Une plateforme d'automatisation de la recette basse tension pilotée par les processus, avec orchestration visuelle du flux de travail et validation par apprentissage automatique

Résumé

La plateforme automatisée d'acceptation en basse tension proposée intègre l'Internet des objets (IoT), l'orchestration visuelle de flux de travail, l'informatique en périphérie et le cloud computing, l'ingénierie des caractéristiques et l'apprentissage automatique afin d'automatiser les tests d'acceptation des systèmes basse tension (BT). La plateforme permet une détection intelligente des défauts, une prise de décision en temps réel, une acceptation automatisée, une grande précision, une faible latence opérationnelle et un déploiement évolutif.

Résumé

The rapid expansion of low-voltage (LV) networks and their integration with distributed energy resources requires intelligent and automated management solutions. Cloud-edge collaborative Internet of Things (IoT) platforms support real-time monitoring, control, and data acquisition. However, existing platforms generally lack workflow automation, visual process orchestration, user-guided decision support, and comprehensive validation. Consequently, they do not provide process-driven solutions for automated LV network acceptance testing. This study presents the design and evaluation of a Low-Voltage Acceptance Automation Platform based on a visualized process canvas. The proposed platform adopts a process-driven architecture in which acceptance workflows are visually created, managed, and executed. The visual process canvas transforms conventional static monitoring into dynamic workflow automation by enabling real-time workflow execution, validation, and decision-making. The framework incorporates the Open LV Network & Smart Meter dataset to support realistic modeling of electrical load behavior. The workflow includes IoT-based data acquisition, data preprocessing, feature engineering, workflow orchestration using the visual process canvas, machine learning-based validation, and real-time dashboard visualization. The proposed framework achieved a fault detection rate of 98.4%, a receiver operating characteristic area under the curve (ROC-AUC) of 0.968, and an operational decision latency of 31 ms, outperforming traditional cloud-centric and IoT-based baseline approaches by approximately 30%–40%.

Introduction

L'industrie 4.0 (I4.0)¹ repose sur plusieurs technologies émergentes, parmi lesquelles l'Internet industriel des objets (IIoT) est l'une des plus importantes. L'IIoT désigne l'application des technologies de l'Internet des objets (IoT) dans les environnements industriels, où des dispositifs et machines interconnectés communiquent principalement par des interactions machine-à-machine. Étant donné que les défaillances des systèmes industriels peuvent entraîner des pertes opérationnelles importantes, les applications de l'IIoT exigent une communication hautement fiable tout en générant des volumes de données nettement plus importants que les systèmes IoT conventionnels². En outre, certaines études considèrent l'IIoT comme un concept étroitement lié à l'industrie 4.0³. Les technologies IoT transforment les architectures hiérarchiques traditionnelles en permettant des systèmes plus flexibles assurant un échange de données fluide⁴. De nombreuses études récentes ont passé en revue les architectures IIoT existantes et proposé de nouvelles conceptions de cadres^5,6,7,8,9. Malgré ces progrès, deux limitations majeures persistent. Premièrement, de nouveaux cadres sont fréquemment proposés afin de pallier les insuffisances des architectures antérieures, ce qui entraîne un nombre croissant de modèles alternatifs augmentant la diversité architecturale et la complexité de mise en œuvre. Deuxièmement, le haut niveau d'abstraction associé à de nombreuses architectures proposées limite leur adoption pratique dans les environnements industriels¹⁰.

Plusieurs architectures de l'IIoT ont été décrites dans la littérature. Une architecture IIoT basée sur la norme Open Platform Communications (OPC) a été présentée conjointement avec un intergiciel Python permettant de gérer la communication OPC¹¹. Une architecture IIoT en sept couches a été proposée dans ; toutefois, les détails de mise en œuvre et les expériences de validation n'ont pas été fournis¹². Un cadre intégrant les technologies 5G et l'IIoT a été décrit conjointement avec un cas d'utilisation représentatif, bien que la validation expérimentale ait été limitée¹³. Un cadre de conception émotionnelle pour l'industrie 4.0 a été introduit, et ses implications potentielles ont été discutées sans vérification expérimentale¹⁴. Une plateforme IIoT multicouche a été évaluée dans un banc d'essai réel, en mettant l'accent sur les considérations liées aux télécommunications¹⁵. De même, un cadre IoT modulaire pour la surveillance de la qualité de l'air intérieur a été présenté dans et ses performances ont été évaluées à l'aide de données recueillies auprès de 84 ménages avec enfants¹⁶.

L'Internet des objets (IoT) est devenu une technologie en évolution rapide, offrant un potentiel considérable pour des applications dans le secteur de l'électricité^17,18. L'intégration des technologies IoT dans les nœuds des systèmes électriques permet une production, un transport, une distribution, une exploitation et une utilisation de l'énergie plus intelligentes et plus efficaces, grâce à une prise de décision autonome appuyée par une surveillance en temps réel continue du flux d'électricité au sein du réseau intelligent. Par conséquent, ces nœuds intelligents améliorent la performance opérationnelle globale du réseau électrique¹⁹. La technologie de communication constitue un élément fondamental de la mise en œuvre des réseaux intelligents, car deux catégories principales d'informations doivent être transmises de manière fiable : les mesures des capteurs et les signaux de commande. Outre une faible latence de communication, les applications des réseaux intelligents exigent une qualité de service (QoS) appropriée et une sécurité des données adéquate afin d'assurer un fonctionnement fiable²⁰.

Le choix d'une technologie de communication appropriée pour les applications de réseau intelligent nécessite de prendre en compte les intervalles de communication, les débits de transmission de données et les coûts de communication²¹. Les réseaux de communication IoT comprennent généralement des couches logicielles, de sécurité, de service, système et de connectivité. Au sein de la couche de connectivité, les protocoles de communication sont généralement classés en trois catégories. Les protocoles longue portée incluent la Long Range (LoRa) et le Narrowband-IoT (NB-IoT) ; les protocoles moyenne portée incluent le Wi-Fi, le 4G/LTE et le 5G ; et les protocoles courte portée incluent le Bluetooth et le ZigBee. Avec la déréglementation croissante des marchés de l'électricité, la prévision de la charge est devenue plus importante pour évaluer les effets des conditions météorologiques, des pannes d'équipement, des changements réglementaires et d'autres facteurs opérationnels sur le coût des services électriques. Par conséquent, une prévision précise de la charge résidentielle est devenue essentielle pour le fonctionnement et la supervision des réseaux intelligents, des micro-réseaux et des bâtiments intelligents²².

Le fonctionnement fiable des réseaux basse tension (BT) dépend du maintien d'une qualité élevée de l'énergie électrique²³. La qualité de l'énergie est déterminée par l'efficacité de la régulation de tension, de l'équilibrage du courant et de l'atténuation des perturbations techniques en cas de conditions de fonctionnement déséquilibrées²⁴. Parmi ces facteurs, l'équilibrage des phases est particulièrement important car il détermine la répartition uniforme des tensions et des courants entre les phases²⁵. Un mauvais équilibrage des phases peut augmenter le chauffage des conducteurs, les écarts de tension et les courants de neutre, réduisant ainsi l'efficacité du système et sa fiabilité opérationnelle²⁶. Par conséquent, l'équilibrage des phases doit être pris en compte lors de la phase de conception afin d'améliorer les performances du système, sa stabilité opérationnelle et sa fiabilité à long terme. Néanmoins, cet aspect est rarement intégré aux méthodologies conventionnelles de conception de mini-réseaux.

De récents progrès dans les systèmes d'orchestration de flux de travail ont démontré les avantages de l'automatisation pilotée par événements et de la gestion visuelle des processus dans les environnements de l'Internet industriel des objets. Néanmoins, leur application à la validation des réseaux de distribution et aux tests d'acceptation en basse tension reste limitée. La plupart des systèmes d'automatisation en basse tension existants se concentrent principalement sur la surveillance et la commande de supervision, tandis que relativement peu d'études explorent la gestion des acceptations pilotée par flux de travail ou la vérification automatisée de la conformité. De même, bien que les techniques d'apprentissage automatique aient suscité un intérêt considérable pour la détection d'anomalies dans les compteurs intelligents et l'évaluation de la qualité de l'énergie, ces approches sont généralement conçues comme des modèles analytiques indépendants plutôt que comme des composants d'un cadre intégré d'orchestration de flux de travail.

Diverses solutions de compteurs d'énergie intelligents pour la gestion des bâtiments intelligents et l'automatisation domestique ont été proposées ces dernières années²⁷. Un prototype de compteur intelligent a été présenté dans la référence²⁷ afin de démontrer l'intégration de concepts éducatifs de niveau universitaire dans les technologies de comptage intelligent. Le compteur intelligent développé a montré un potentiel significatif pour la gestion et le contrôle de l'énergie, réduisant la consommation d'énergie et profitant à la fois aux fournisseurs et aux consommateurs grâce à une communication IoT bidirectionnelle. Un système de prise intelligente basé sur un microcontrôleur a ensuite été introduit pour soutenir une surveillance intelligente de l'énergie²⁸.

Le système de prise intelligente proposé affiche en temps réel la consommation d'énergie via une interface graphique basée sur Android. En outre, l'appareil peut détecter la présence d'appareils électriques connectés, une fonctionnalité appelée mesure invasive de la charge²⁸. Une prise intelligente commerciale peu coûteuse a été utilisée pour la mise en œuvre. Les améliorations futures incluent la surveillance du courant efficace (RMS), de la puissance active, de la puissance réactive et de l'angle de phase entre la tension et le courant. Comme décrit dans nos études précédentes, une microrégion photovoltaïque partiellement raccordée au réseau utilise les protocoles de communication ZigBee et LoRa pour échanger des informations avec des dispositifs de comptage intelligent, démontrant ainsi la faisabilité d'une communication activée par l'Internet des objets (IoT) pour les systèmes d'énergie distribués^29,30.

Pour pallier les limites de la planification conventionnelle des systèmes de distribution, les pratiques d'ingénierie et la recherche scientifique ont progressé selon plusieurs axes complémentaires. Une première direction de recherche s'est concentrée sur la planification stratégique à l'aide de systèmes d'information géographique (SIG) pour la sélection des sites et l'évaluation préliminaire des ressources^31,32. Une autre direction a porté sur l'amélioration de composants et de sous-systèmes individuels, notamment le choix des conducteurs, le dimensionnement optimal de la production et du stockage d'énergie, ainsi que des évaluations comparatives des systèmes de distribution en courant alternatif (AC) et en courant continu (DC)^33,34,35,36. Une troisième voie de recherche a appliqué des algorithmes d'optimisation à la planification des réseaux de distribution, au tracé des alimentations et à la conception de la topologie du réseau. Parmi les avancées récentes figurent des cadres tels que la plateforme uGrid des chercheurs, qui intègre le positionnement des dispositifs et la configuration du réseau, mais ne dispose pas d'une analyse standard de flux de puissance pour la vérification et l'optimisation. D'autres approches s'appuient sur un réglage manuel des paramètres pour la génération de topologies ou se concentrent sur des applications spécialisées, comme les microréseaux DC à faible puissance^37,38,39. Bien que ces approches représentent des progrès significatifs, des travaux supplémentaires sont nécessaires pour établir une méthodologie intégrée permettant une conception complète des systèmes de distribution en basse tension. En outre, les évaluations techno-économiques exhaustives des systèmes monophasés, triphasés et hybrides en basse tension restent limitées.

Les récents progrès réalisés dans le domaine de l'intelligence artificielle (IA) et de l'apprentissage automatique ont encore élargi les capacités des systèmes électriques intelligents. Une revue complète présentée dans a résumé les applications de l'IA et de l'apprentissage automatique dans les réseaux intelligents, incluant des technologies émergentes telles que l'apprentissage fédéré, l'IA générative, les grands modèles linguistiques, l'intelligence artificielle des objets (IAoT) et les jumeaux numériques⁴⁰. Cette revue a mis en lumière des applications dans la prévision de charge, la maintenance prédictive, la détection d'anomalies, la gestion côté demande et l'intégration des véhicules électriques, tout en soulignant les défis persistants liés à l'interopérabilité, à la confidentialité, à l'évolutivité, à la robustesse et aux considérations éthiques. Une autre revue récente a évalué les méthodes d'IA pour la gestion décentralisée de l'énergie dans les infrastructures IoT-bords-nuage, en se concentrant sur l'apprentissage automatique, l'apprentissage par renforcement et les systèmes multi-agents pour le contrôle décentralisé de l'énergie⁴¹.

Dans leur ensemble, les études antérieures ont fait progresser la surveillance activée par l'Internet des objets (IoT), la comptabilité intelligente, l'informatique cloud-edge, l'intelligence artificielle et la gestion intelligente de l'énergie pour les systèmes de distribution basse tension (LV). Toutefois, ces technologies ont été principalement développées indépendamment. L'orchestration des flux de travail, la gestion automatisée des validations, la validation pilotée par processus et l'aide à la décision intégrée restent limitées, ce qui souligne le besoin d'un cadre unifié d'automatisation orienté vers les flux de travail.

En conséquence, cette étude présente une plateforme automatisée d'acceptation basse tension basée sur un canevas de processus visualisé. Le cadre proposé intègre l'acquisition de données fondée sur l'Internet des objets (IoT), le prétraitement des données, l'ingénierie des caractéristiques, l'orchestration des flux de travail, la validation assistée par apprentissage automatique, le calcul nuage-bord (cloud-edge) et la visualisation en temps réel au sein d'une architecture unifiée, afin de soutenir des tests automatisés et fiables d'acceptation des réseaux BT à l'aide de données réelles provenant de compteurs intelligents. Figure 1 présente un aperçu de l'architecture orientée flux de travail de la plateforme proposée. Le flux de travail comprend l'acquisition de données, le prétraitement, l'ingénierie des caractéristiques, l'orchestration des flux de travail, la prise de décision intelligente et l'intégration nuage-bord, permettant ainsi une validation automatisée des réseaux de distribution BT au moyen d'un cadre orienté processus. La plateforme a démontré une grande précision de validation tout en réduisant la latence des décisions opérationnelles et le temps d'exécution du flux de travail par rapport aux approches conventionnelles.

Figure 1. Architecture orientée processus de la plateforme automatisée de réception basse tension proposée. Architecture de haut niveau de la plateforme automatisée de réception basse tension (BT) pilotée par les processus. Le cadre illustre l'intégration séquentielle de l'acquisition de données activée par l'internet des objets (IdO), du prétraitement des données, de l'ingénierie des caractéristiques, de l'orchestration des flux de travail, de la prise de décision intelligente, de la collaboration cloud-edge et de la réception automatisée pour la validation du réseau de distribution basse tension. IdO = Internet des objets ; BT = basse tension ; ML = apprentissage automatique. Veuillez cliquer ici pour afficher une version agrandie de cette figure.

Protocole

This study did not involve human participants, animals, or identifiable personal data. The analyses were performed using a publicly available dataset (UK Power Networks Open LV Network & Smart Meter dataset) together with synthetically generated data for validation; therefore, ethics committee approval and informed consent were not required. The research tools used in the protocol are listed in the Table of Materials.

1. Data acquisition

The Low-Voltage (LV) Acceptance Automation Platform was developed using electrical measurements acquired from smart meters, IoT sensors, and the Open LV Network & Smart Meter Dataset. Electrical parameters, including voltage, current, active power, reactive power, and energy consumption, were collected through Wi-Fi-, PLC-, and RS-485-based communication protocols. Real-time measurements were used for live system monitoring, whereas historical data supported model development and validation.

The proposed framework used the Open LV Network & Smart Meter Dataset provided by UK Power Networks⁴². The dataset comprises household smart meter consumption, feeder-level load profiles, and feeder voltage measurements. Time-series subsets containing load consumption and voltage data were selected for model training and evaluation. In addition, a simulated smart meter dataset was generated to represent operational conditions and fault scenarios required for workflow validation and machine learning model evaluation. The simulated dataset included timestamped measurements of voltage, current, active power, reactive power, energy consumption, total harmonic distortion (THD), and voltage imbalance. Fault samples were generated by simulating undervoltage, overvoltage, excessive harmonic distortion, and voltage imbalance based on established low-voltage operational thresholds. The dataset characteristics are summarized in Table 1.

Attribute	Description
Dataset Name	Open LV Network & Smart Meter Dataset
Simulated  Smart Meter Dataset	Geneated 1000 smaples for Fault simulation and workflow validation
Data Type	Time-series (historical smart meter data)
Data Granularity	Household-level and feeder-level measurements
Key Features	Voltage, current, active power, reactive power, energy consumption, timestamps
Data Frequency	High-resolution (e.g., half-hourly / minute-level depending on subset)
Coverage	Residential low-voltage distribution networks
Usage in Proposed Work	Model training, validation, load behavior analysis, and acceptance workflow evaluation

Table 1: Dataset description. Summary of the Open LV Network & Smart Meter dataset used for model development and performance evaluation. The table presents the dataset components, measured electrical variables, sampling characteristics, and dataset partitioning for training, validation, and testing.

Because the Open LV Network & Smart Meter Dataset does not contain predefined fault labels, a rule-based labeling strategy was applied to both the real and simulated datasets. Samples satisfying normal operating limits were assigned a label of 0 (Normal), whereas samples exceeding operational thresholds (e.g., voltage deviations greater than ±10% of the nominal voltage, THD > 5%, or voltage unbalance > 2%) were assigned a label of 1 (Fault). These labels served as the ground truth during model training, validation, and testing. The proposed rule engine also allows threshold values to be configured in accordance with regional standards or utility-specific acceptance criteria.

The dataset was partitioned into training (70%), validation (15%), and testing (15%) subsets. Missing values were addressed using linear interpolation, mean imputation, and forward-fill techniques as described in the preprocessing stage. To ensure statistical robustness and reproducibility, all experiments were repeated five times using different random seeds.

2. Data preprocessing

Raw data from the Open LV Network & Smart Meter Dataset and IoT sensor measurements were preprocessed to improve data quality prior to feature extraction and model development. Missing values, noise, and inconsistencies caused by communication interruptions and sensor malfunctions were identified and corrected using interpolation, mean imputation, and forward-fill techniques. The detailed mathematical derivations are provided in Supplementary File 1 (Section S1).

The preprocessed time-series data were segmented into representative operational intervals (S₁–S₅ and S_k). Statistical and electrical features, including average load, peak load, minimum load, standard deviation, voltage deviation, and power consumption, were extracted from each segment. The extracted features are summarized in Table 2 and served as inputs for the subsequent feature engineering stage.

Segment ID	Mean Load (kW)	Peak Load (kW)	Min Load (kW)	Std Deviation (kW)	Voltage Deviation (p.u.)	Power Consumption (kWh)	Time Interval
S₁	2.45	3.8	1.2	0.65	0.032	58.4	00:00–01:00
S₂	2.9	4.1	1.5	0.72	0.028	64.2	01:00–02:00
S₃	3.25	4.85	1.8	0.81	0.035	71.6	02:00–03:00
S₄	3.8	5.2	2.1	0.9	0.041	78.9	03:00–04:00
S₅	4.1	5.75	2.4	0.95	0.045	85.3	04:00–05:00
Sk	3.6	5.1	2	0.88	0.038	76.5	tk

Table 2: Representative feature representation extracted from time-series segments. Representative statistical, electrical, load behavior, voltage stability, and power quality features extracted from segmented LV time-series data during feature engineering. The values illustrate the engineered feature representation and are not experimental performance results. LF = Load Factor; PAR = Peak-to-Average Ratio; VSI = Voltage Stability Index; PF = Power Factor; THD = Total Harmonic Distortion.

3. Feature engineering

Feature engineering was performed to improve the representation of the preprocessed data for workflow orchestration and intelligent decision-making. Principal Component Analysis (PCA)^43 was applied to reduce data dimensionality by removing redundant and highly correlated variables while retaining the most informative feature components. The mathematical derivations are provided in Supplementary File 1 (Section S2).

Statistical descriptors, load behavior indicators, voltage stability indices, and power quality metrics were derived from the segmented time-series data. These engineered features included Load Factor (LF), Peak-to-Average Ratio (PAR), Voltage Stability Index (VSI), Voltage Unbalance Index, Power Factor (PF), and Total Harmonic Distortion (THD). The resulting feature set was used as the input to the workflow orchestration and intelligent decision-making modules.

The feature engineering workflow is summarized in Supplementary File 1 (Supplementary Algorithm 1). The procedure consisted of segmenting the preprocessed data, extracting statistical and electrical features, calculating load behavior, voltage stability, and power quality indicators, and applying PCA to generate the final feature vector used for model training and validation.

4. Visualized process canvas design

The Visualized Process Canvas was developed as a graph-based workflow orchestration framework for automating low-voltage (LV) acceptance procedures. The workflow was represented as a directed graph, G = (N, E), where N = {n₁, n₂, …, n_m}denotes the workflow nodes corresponding to individual processing stages (e.g., data input, preprocessing, validation, and decision-making), and E = {e_ij}represents the directed edges defining the execution sequence between nodes. This graph-based representation enabled the creation of configurable workflows and their automated execution without manual coding.

Each workflow node performed a specific processing task by receiving input data, executing predefined operations, and forwarding the processed output to subsequent nodes. Acceptance criteria, including voltage and load thresholds, were implemented as configurable validation rules that could be updated without modifying the workflow structure. The workflow supported both sequential and parallel execution to improve computational efficiency. Machine learning models were integrated into designated workflow nodes to perform anomaly detection and automated acceptance validation (Figure 2).

Figure 2: Visualized process canvas architecture for LV acceptance automation. Overview of the visual workflow orchestration framework used for LV acceptance automation. The process canvas illustrates the graphical organization of workflow nodes for data processing, feature engineering, rule-based validation, intelligent decision-making, and output generation to support workflow design, execution, and monitoring. Please click here to view a larger version of this figure.

The mathematical formulation describing information flow through the workflow graph is provided in Supplementary File 1 (Section S3). Supplementary File 1 (Supplementary Algorithm 2) describes the workflow orchestration procedure, including workflow traversal, node execution, rule validation, decision generation, and output aggregation.

The Visualized Process Canvas was implemented using a microservice-oriented software architecture to support scalability and modular deployment. The graphical workflow interface was developed using React.js to provide drag-and-drop workflow configuration. Backend orchestration services were implemented using Flask/FastAPI, while Eclipse Mosquitto served as the MQTT message broker for communication between workflow modules. EdgeX Foundry provided edge device management and IoT integration. Machine learning services were implemented with Scikit-learn, TensorFlow, and PyTorch, and containerized with Docker and Kubernetes.

5. Workflow orchestration engine

The workflow orchestration engine coordinated execution of the configured acceptance workflow. A detailed description is provided in Supplementary File 1 (Section S4), and the execution sequence is summarized in Supplementary Figure 1.

The workflow execution process consisted of validating the workflow definition, initializing the execution environment, scheduling workflow nodes according to their dependencies, executing nodes sequentially or in parallel, applying rule-based validation, aggregating intermediate outputs, and generating the final acceptance or rejection decision based on rule-based and machine learning evaluation. Execution results were published through dashboards, reports, application programming interfaces (APIs), and data storage services. The overall workflow orchestration process is illustrated in Figure 3.

Figure 3: Comparison of classification performance metrics across different methods. Comparison of the classification performance of IoT-LV, RBM, Support Vector Machine (SVM), Random Forest (RF), Long Short-Term Memory (LSTM), and the proposed framework using the Open LV Network & Smart Meter dataset. Performance is evaluated using Accuracy, Precision, Recall, and F1-score. Results are presented as mean ± standard deviation (SD) from five independent experimental runs using a 70%/15%/15% training/validation/testing split. Error bars represent one standard deviation. Please click here to view a larger version of this figure.

6. Intelligent decision module

The Intelligent Decision Module was developed to automate low-voltage (LV) acceptance decisions using supervised machine learning models. Classification and regression algorithms were applied to the engineered feature vectors to support operational decision-making. Classification models identified normal and abnormal operating conditions, whereas regression models estimated future energy consumption and operational trends.

The input feature vector, X ∈ ℝ^d, comprised the statistical, voltage stability, load behavior, and power quality features extracted during the feature engineering stage. Standalone Support Vector Machine (SVM)⁴⁴, Random Forest (RF)⁴⁵, and Long Short-Term Memory (LSTM)⁴⁶ models were implemented as baseline classifiers for comparative evaluation. The mathematical formulation of the learning models is provided in Supplementary File 1 (Section S5).

For classification, the output variable y ∈ {0,1} represented normal (0) and abnormal (1) operating conditions. When abnormal operating conditions or overload events were detected, the workflow generated a fault notification and flagged the acceptance process as invalid; otherwise, the process was classified as accepted.

The workflow orchestration engine integrated machine-learning predictions with rule-based validation, using a priority-based conflict-resolution strategy. Safety-critical operational rules and regulatory acceptance criteria were treated as hard constraints and therefore took precedence over machine-learning predictions when conflicts occurred. Final acceptance decisions were generated using the combined outputs of the rule-based validation and intelligent decision modules.

7. Cloud–edge integration and visualization dashboard

A cloud-edge computing architecture was implemented to support scalable data processing, storage, and visualization for the LV acceptance automation platform. Smart meters, SCADA systems, and IoT devices continuously collect electrical measurements, which are processed at the edge layer via filtering, normalization, feature extraction, and real-time inference to reduce communication overhead and enable low-latency decision-making. The mathematical derivations are provided in Supplementary File 1 (Section S6).

Processed data were transmitted to the cloud layer for long-term storage, advanced analytics, feature engineering, model training, and model management. Interactive dashboards provided real-time system monitoring, alerts, reporting, and operational decision support. The cloud-edge architecture is illustrated in Supplementary Figure 2, and the implementation details are summarized in Table 3.

Layer	Component	Hardware / Software	Specification / Version	Purpose / Description
Edge Layer	Edge Device	Raspberry Pi 4 / NVIDIA Jetson Nano	Quad-core CPU, 4–8 GB RAM	Real-time data acquisition and local processing
	IoT Gateway	Industrial IoT Gateway	MQTT / Modbus / OPC-UA support	Communication between sensors and edge/cloud
	Sensors / Smart Meters	Digital Smart Meters	Voltage, Current, Power Measurement	Data collection from LV network
	Edge Software	Python, EdgeX Foundry, MQTT Broker	Python 3.x	Data preprocessing, filtering, local inference
	Communication Protocols	Wi-Fi / PLC / RS-485	Standard protocols	Data transmission to cloud layer
Cloud Layer	Cloud Platform	AWS / Microsoft Azure / Google Cloud	Scalable cloud services	Data storage, analytics, and model training
	Storage	AWS S3 / Azure Blob / InfluxDB	Time-series database	Storing historical and real-time data
	Compute & ML	Python, TensorFlow, PyTorch, Scikit-learn	ML libraries (latest versions)	Model training, evaluation, deployment
	Containerization	Docker, Kubernetes	Latest stable versions	Workflow orchestration and scalability
	Data Processing	Apache Spark / Pandas	Distributed processing	Large-scale data analytics
Visualization Layer	Dashboard Tools	Grafana / Apache Superset / Plotly Dash	Web-based tools	Real-time monitoring and visualization
	Web Framework	React.js / Angular / Flask / FastAPI	Modern web stack	UI development and API integration
	Notification System	Email / SMS Gateway / Push Notifications	Twilio / Firebase	Alert generation and communication
	API Services	REST APIs	JSON-based communication	Integration between modules

Table 3: System implementation details. Summary of the hardware configuration, software environment, communication protocols, and cloud–edge computing components used for implementing the proposed LV acceptance automation platform.

Résultats

The performance of the proposed Low-Voltage (LV) Acceptance Automation Platform was evaluated using the Open LV Network & Smart Meter Dataset together with a synthetic smart meter dataset generated to represent additional operating conditions and fault scenarios. The synthetic dataset enabled controlled evaluation of workflow orchestration, intelligent decision-making, and fault detection under abnormal operating conditions. The Open LV Network & Smart Meter Dataset comprised household smart meter measurements, feeder-level load profiles, and voltage measurements. Time-series segments corresponding to load consumption and voltage variations were extracted for model development and evaluation.

The dataset was partitioned into training (70%), validation (15%), and testing (15%) subsets. The proposed LV Acceptance Automation Platform achieved high classification accuracy (approximately 96%–98%), effective fault detection capability, and reduced operational decision latency. To ensure statistical robustness and reproducibility, all experiments were repeated five independent times using different random seeds. The resulting performance distributions were subsequently analyzed using paired t-tests, one-way analysis of variance (ANOVA), Tukey's honestly significant difference (HSD) post-hoc analysis, and 95% confidence intervals. The simulation environment used for implementing the proposed framework is summarized in Table 4.

Parameter	Value	Description
Dataset	Open LV Network & Smart Meter Dataset + Synthetic Smart Meter Dataset	Real-world and simulated LV network data
Total Samples	1000 synthetic samples + selected Open LV subsets	Data used for validation and testing
Data Split	70% Training / 15% Validation / 15% Testing	Model development and evaluation
Number of Independent Runs	5	Statistical reliability analysis
Random Seeds	42, 52, 62, 72, 82	Reproducible experimental setup
Total Statistical Observations	30 observations (6 models × 5 runs)	Used for t-test, ANOVA, and Tukey HSD
Sampling Rate	30-min / 1-min intervals	Time-series resolution
Features	Load, Voltage, Current, Active Power, Reactive Power, THD, Voltage Unbalance, Derived Features	Input features for ML models
ML Models	Random Forest, SVM, XGBoost, LSTM	Intelligent decision module
Hardware	NVIDIA RTX 3090 GPU, Intel Core i9 CPU, 64 GB RAM	Training and simulation environment
Edge Device	Raspberry Pi 4 / Jetson Nano	Edge inference and real-time processing
Software	Python 3.10, TensorFlow 2.12+, Scikit-learn 1.3+, PyTorch 2.0+	Model implementation
Communication Protocols	MQTT / HTTP / RS-485	Data transmission
Threshold Values	Voltage ±10%, THD > 5%, Voltage Unbalance > 2%, Feeder Load > 90% capacity	Fault labeling and validation rules
Statistical Tests	Paired t-test, One-way ANOVA, Tukey HSD, 95% Confidence Interval	Performance significance evaluation

Table 4: Simulation environment. Configuration of the experimental environment, including dataset partitioning, machine learning models, hardware specifications, software environment, and validation protocol. Experiments were performed using a 70% training, 15% validation, and 15% testing split and repeated five times using different random seeds.

Classification performance

The proposed framework was evaluated using multiple performance metrics, including accuracy, precision, recall, F1-score, latency, and fault detection rate. Accuracy was used to assess overall classification performance, whereas precision, recall, and F1-score evaluated the effectiveness of fault detection. Latency measured the operational decision response time of the workflow, and the fault detection rate quantified the ability of the framework to identify abnormal operating conditions within the LV distribution network. Scalability was further assessed by progressively increasing the number of input data samples.

The proposed LV Acceptance Automation Platform was compared with five benchmark approaches, namely IoT-LV, Rule-Based Monitoring (RBM), Support Vector Machine (SVM), Random Forest (RF), and Long Short-Term Memory (LSTM). The IoT-LV framework primarily supports data acquisition and basic monitoring using predefined threshold criteria without intelligent decision-making capabilities. Similarly, the RBM approach relies on fixed operational thresholds and therefore lacks adaptive learning. Although SVM and RF effectively classify operational data through supervised learning, they do not incorporate workflow orchestration or integrated acceptance management. LSTM provides improved temporal learning for time-series analysis but does not support automated workflow execution. In contrast, the proposed framework combines workflow orchestration, hybrid rule-based and machine learning decision-making, feature engineering, and cloud-edge computing within a unified automation architecture.

To ensure a fair comparison, all baseline methods were evaluated using the same training, validation, and testing partitions (70%, 15%, and 15%, respectively). Hyperparameter optimization for the machine learning baselines was performed using the validation dataset, and all models employed identical preprocessing and feature-scaling procedures. Unlike the standalone SVM⁴⁴, RF⁴⁵, and LSTM⁴⁶ classifiers, which were trained directly on the original feature space, the proposed framework incorporated advanced feature engineering, workflow validation, and acceptance-rule orchestration prior to classification.

The classification performance of all methods is summarized in Table 5. Among the conventional approaches, IoT-LV achieved the lowest classification accuracy (82.4%) because of its reliance on conventional monitoring without intelligent decision-making. RBM slightly improved performance, reaching an accuracy of 85.7%; however, its fixed validation thresholds limited adaptability. Machine learning approaches demonstrated progressively better performance, with SVM and RF achieving accuracies of 91.6% and 93.4%, respectively, owing to their ability to learn discriminative patterns from the data. LSTM further improved the classification accuracy to 95.2% by effectively capturing temporal dependencies within the smart meter time-series data.

The proposed LV Acceptance Automation Platform achieved the best overall classification performance, with an accuracy of 97.3%, precision of 96.8%, recall of 96.1%, and an F1-score of 96.4%. These improvements are attributable to the integration of advanced preprocessing, feature engineering, workflow orchestration, hybrid rule-based and machine learning decision-making, and cloud-edge collaborative processing rather than the application of the machine learning algorithms alone. Collectively, these components enhanced the separability between normal and abnormal operating conditions while improving the efficiency of automated acceptance validation.

The comparative classification performance of all evaluated methods is illustrated in Figure 3.

Method	Accuracy (%)	Precision (%)	Recall (%)	F1-Score (%)
IoT-LV	82.4	80.2	78.5	79.3
RBM	85.7	83.9	82.1	83
SVM	91.6	90.8	89.7	90.2
RF	93.4	92.6	91.8	92.2
LSTM	95.2	94.5	93.8	94.1
Proposed Method	97.3	96.8	96.1	96.4

Table 5: Comparison of classification metrics. Comparison of the classification performance of IoT-LV, RBM, SVM, RF, LSTM, and the proposed framework using Accuracy, Precision, Recall, and F1-score. Results are reported as mean ± standard deviation (SD) obtained from five independent experimental runs.

Statistical significance analysis

To further evaluate the reliability of the proposed LV Acceptance Automation Platform, statistical significance testing was performed to compare its performance with the benchmark methods, including IoT-LV, RBM, SVM, RF, and LSTM. Multiple experimental runs were conducted using different train-validation-test partitions of the Open LV Network & Smart Meter Dataset. The resulting classification accuracies were used to calculate the mean and standard deviation for each method, followed by paired t-tests to determine whether the observed performance differences were statistically significant. The mathematical formulation of the paired t-test is provided in Supplementary File 1 (Section S7).

A significance level of 0.05 was adopted for all statistical analyses. To ensure reproducibility, each experiment was repeated five independent times using different random seeds and data partitions. The performance metrics obtained from each run were subsequently used for statistical evaluation.

The paired t-test results are summarized in Table 6. The proposed framework significantly outperformed all benchmark methods (p < 0.05), demonstrating statistically significant improvements in accuracy, precision, recall, and F1-score. Significant performance gains were observed not only over conventional approaches such as IoT-LV and RBM but also over the more advanced machine learning models, including SVM, RF, and LSTM. These findings indicate that the observed improvements were not attributable to random variation but resulted from the integrated workflow-oriented automation framework.

Comparison	p-value	Significance
Proposed vs IoT-LV	0.0008	Significant
Proposed vs RBM	0.0015	Significant
Proposed vs SVM	0.012	Significant
Proposed vs RF	0.021	Significant
Proposed vs LSTM	0.034	Significant

Table 6: Pairwise statistical significance analysis (p-values). Pairwise statistical comparison between the proposed framework and the benchmark methods. The table reports p-values obtained from statistical significance testing, where p < 0.05 indicates a statistically significant difference.

Receiver operating characteristic (ROC) analysis

Receiver operating characteristic (ROC) analysis was performed to further evaluate the classification capability of the proposed LV Acceptance Automation Platform in comparison with IoT-LV, RBM, SVM, RF, and LSTM. The area under the ROC curve (AUC) was used to quantify the discrimination capability of each classifier by evaluating the trade-off between the true positive rate (TPR) and false positive rate (FPR).

The IoT-LV framework achieved the lowest AUC (approximately 0.690), reflecting its reliance on conventional monitoring without intelligent decision-making. RBM produced a moderate AUC of approximately 0.738 because of its dependence on fixed threshold-based validation rules. The machine learning classifiers demonstrated progressively improved performance, with SVM and RF achieving AUC values of approximately 0.833 and 0.861, respectively, owing to their ability to learn discriminative patterns from operational data. LSTM further improved classification performance, achieving an AUC of approximately 0.885 by effectively modeling temporal dependencies in smart meter time-series data.

The proposed LV Acceptance Automation Platform achieved the highest AUC (approximately 0.910), demonstrating superior discrimination between normal and abnormal operating conditions. This improvement is attributed to the combined effects of advanced feature engineering, workflow orchestration, hybrid rule-based and machine learning decision-making, and cloud-edge collaborative processing. The comparative ROC curves for all evaluated methods are presented in Figure 4.

Figure 4: Receiver operating characteristic (ROC) curve comparison for LV acceptance Automation. Comparison of the Receiver Operating Characteristic (ROC) curves for IoT-LV, RBM, SVM, RF, LSTM, and the proposed framework. The Area Under the ROC Curve (ROC-AUC) evaluates classification performance across different decision thresholds. TPR denotes True Positive Rate, and FPR denotes False Positive Rate. Please click here to view a larger version of this figure.

ANOVA-based statistical significance analysis

To further validate the experimental results, a one-way analysis of variance (ANOVA) was performed to compare the performance of the proposed framework with IoT-LV, RBM, SVM, RF, and LSTM. Whereas the paired t-test evaluates differences between two methods, ANOVA determines whether statistically significant differences exist among multiple groups simultaneously. The ANOVA analysis was conducted using repeated experiments with different train-validation-test partitions of the Open LV Network & Smart Meter Dataset. The mathematical derivations are presented in Supplementary File 1 (Section S8).

The ANOVA results are presented in Table 7. A large F-statistic (approximately 18.7) with p < 0.001, obtained from 30 observations across five independent experimental runs, demonstrated statistically significant differences among the evaluated methods.

Source of Variation	SS	df	MS	F-value	p-value
Between Groups	412.6	5	82.52	18.7	< 0.001
Within Groups	132.4	30	4.41	—	—
Total	545	35	—	—	—

Table 7: One-Way analysis of variance (ANOVA) results. Results of the one-way ANOVA performed to evaluate statistical differences among the compared methods. The table reports the F-statistic, degrees of freedom (df), and corresponding p-values.

To identify the specific methods responsible for these differences, Tukey's honestly significant difference (HSD) post-hoc analysis was subsequently performed. The results are summarized in Table 8 and showed that the proposed LV Acceptance Automation Platform significantly outperformed IoT-LV, RBM, SVM, and RF while also achieving statistically significant improvements over LSTM. These findings further confirm the effectiveness of integrating workflow orchestration, feature engineering, hybrid rule-based and machine learning decision-making, and cloud-edge computing within a unified acceptance automation framework.

Comparison	p-value	Significance
Proposed vs IoT-LV	< 0.001	Significant
Proposed vs RBM	< 0.001	Significant
Proposed vs SVM	0.009	Significant
Proposed vs RF	0.018	Significant
Proposed vs LSTM	0.041	Significant

Table 8: Tukey honestly significant difference (HSD) post-hoc analysis. Pairwise comparisons among the evaluated methods using the Tukey HSD post-hoc test following ANOVA. The table reports mean differences, confidence intervals (CI), adjusted p-values, and statistical significance.

Confidence interval analysis

The reliability and consistency of the proposed framework were further evaluated by calculating 95% confidence intervals (CI) for the classification accuracy obtained from repeated experiments. The computational procedure is described in Supplementary File 1 (Section S8).

The confidence interval analysis is summarized in Table 9. Conventional approaches, including IoT-LV and RBM, exhibited relatively wide confidence intervals, indicating greater variability in classification performance. In contrast, the machine learning-based methods (SVM, RF, and LSTM) demonstrated narrower confidence intervals, reflecting improved stability across repeated experiments.

Method	Mean Accuracy (%)	Std. Dev (%)	95% Confidence Interval (%)
IoT-LV	82.4	1.8	[81.0, 83.8]
RBM	85.7	1.6	[84.5, 86.9]
SVM	91.6	1.3	[90.6, 92.6]
RF	93.4	1.2	[92.5, 94.3]
LSTM	95.2	1	[94.5, 95.9]
Proposed Method	97.3	0.8	[96.7, 97.9]

Table 9: Confidence intervals for classification accuracy. Mean classification accuracy, standard deviation (SD), and 95% confidence interval (CI) for each evaluated method based on five independent experimental runs. The table summarizes the statistical variability and reliability of the classification performance.

The proposed LV Acceptance Automation Platform achieved the highest mean classification accuracy (97.3%) together with the narrowest 95% confidence interval (96.7%–97.9%), indicating excellent consistency and robustness. Furthermore, the absence of overlap between the confidence interval of the proposed framework and those of the benchmark methods provides additional evidence of its statistically superior performance.

Forecasting performance

In addition to classification performance, the forecasting capability of the proposed LV Acceptance Automation Platform was evaluated using the root mean square error (RMSE) and mean absolute error (MAE). These metrics quantify the accuracy of energy consumption prediction by measuring the deviation between the predicted and observed values.

The forecasting performance of the proposed framework and the benchmark methods is summarized in Table 10. The corresponding confusion matrix heatmaps for the evaluated classification methods are presented in Figure 5, illustrating the distributions of true positive, true negative, false positive, and false negative predictions. The proposed framework achieved the lowest prediction errors, with an RMSE of 2.1 and an MAE of 1.6, demonstrating superior forecasting performance compared with IoT-LV, RBM, SVM, RF, and LSTM. Prediction errors progressively decreased from the conventional IoT-LV and RBM approaches to the machine learning-based SVM, RF, and LSTM models, highlighting the advantages of intelligent learning techniques. The proposed framework further reduced prediction errors by integrating advanced feature engineering, workflow orchestration, hybrid rule-based and machine learning decision-making, and cloud-edge collaborative processing, thereby improving the accuracy and reliability of energy consumption forecasting. Operational decision latency for the evaluated methods is compared in Figure 6. The proposed framework achieved the shortest decision latency, demonstrating the effectiveness of workflow orchestration and cloud-edge collaborative processing.

Method	RMSE	MAE
IoT-LV	8.9	7.2
RBM	7.6	6.1
SVM	5.1	4.3
RF	4.2	3.5
LSTM	3.4	2.8
Proposed Method	2.1	1.6

Table 10: Comparison of forecasting error metrics (RMSE and MAE). Comparison of the forecasting performance of IoT-LV, RBM, SVM, RF, LSTM, and the proposed framework using Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). Lower RMSE and MAE values indicate smaller prediction errors.

Figure 5: Comparison of confusion matrix heatmaps. Confusion matrices for IoT-LV, RBM, SVM, RF, LSTM, and the proposed framework showing classification outcomes in terms of True Positive (TP), True Negative (TN), False Positive (FP), and False Negative (FN). The heatmaps illustrate the distribution of correctly and incorrectly classified samples for each method. Please click here to view a larger version of this figure.

Figure 6: Comparison of operational decision latency across different methods. Comparison of the operational decision latency of IoT-LV, RBM, SVM, RF, LSTM, and the proposed framework during LV acceptance automation. Latency is measured in milliseconds (ms) and represents the operational decision time required for workflow execution, rule validation, and acceptance decision generation. Please click here to view a larger version of this figure.

Ablation study

The contribution of each major component of the proposed LV Acceptance Automation Platform was evaluated through an ablation study. The framework was progressively constructed by enabling feature engineering, intelligent machine-learning decision-making, workflow orchestration, and cloud-edge integration. The baseline configuration, in which none of these modules was enabled, achieved an accuracy of 82.6%, an F1-score of 80.4%, an RMSE of 8.7, and an operational latency of 96 ms, demonstrating the limitations of conventional processing without intelligent automation.

The ablation results are summarized in Table 11. Progressive incorporation of feature engineering substantially improved classification performance by enhancing the representation of operational characteristics extracted from the smart meter data. Adding the intelligent decision module further increased classification accuracy and reduced prediction errors through data-driven decision-making. Integration of workflow orchestration improved automation efficiency by coordinating validation, execution, and decision processes, while cloud-edge collaboration reduced operational decision latency through distributed processing. Collectively, these modules produced consistent improvements in accuracy and F1-score while simultaneously reducing RMSE and execution latency.

The complete LV Acceptance Automation Platform achieved the best overall performance, with a classification accuracy of 97.3%, an F1-score of 96.4%, an RMSE of 2.1, and an operational latency of 31 ms. These findings demonstrate that the observed performance improvements result from the integration of workflow orchestration, advanced feature engineering, hybrid rule-based and machine-learning decision-making, and cloud-edge collaboration, rather than from any individual component alone. The fault detection performance of the evaluated methods is presented in Figure 7, where the proposed framework achieved the highest fault detection rate. Figure 8 illustrates the scalability analysis, demonstrating that the proposed framework maintained the lowest processing time as the dataset size increased, confirming its suitability for large-scale LV acceptance automation.

Configuration	Workflow Orchestration	Feature Engineering	Cloud–Edge Processing	Intelligent ML Decision Module	Accuracy (%)	F1-Score (%)	RMSE	Latency (ms)
Baseline System	✗	✗	✗	✗	82.6	80.4	8.7	96
+ Feature Engineering	✗	✓	✗	✗	88.9	87.5	6.2	84
+ ML Decision Module	✗	✓	✗	✓	92.8	91.6	4.5	63
+ Workflow Orchestration	✓	✓	✗	✓	95.1	94.2	3.3	48
+ Cloud–Edge Integration	✓	✓	✓	✓	97.3	96.4	2.1	31

Table 11: Ablation study of the proposed framework. Experimental evaluation of the contribution of feature engineering, intelligent decision-making, workflow orchestration, and cloud-edge integration to the overall performance of the proposed framework. Performance is reported for each incremental configuration using Accuracy, F1-score, RMSE, and Operational Decision Latency.

Figure 7. Comparison of fault detection rate across different methods. Comparison of the fault detection performance of IoT-LV, RBM, SVM, RF, LSTM, and the proposed framework using the Open LV Network & Smart Meter dataset. Fault Detection Rate (%) represents the proportion of correctly identified fault conditions. Please click here to view a larger version of this figure.

Figure 8. Scalability analysis of different methods. Comparison of the scalability of IoT-LV, RBM, SVM, RF, LSTM, and the proposed framework under increasing dataset sizes. Scalability is evaluated using processing time (ms) as computational workload increases. Please click here to view a larger version of this figure.

DATA AVAILABILITY:

The Open LV Network & Smart Meter dataset used in this study is publicly available through the UK Power Networks Open Data Portal⁴² at: https://ukpowernetworks.opendatasoft.com/explore/assets/ukpn-smart-meter-consumption-lv-feeder/. All study-generated resources, including the simulated smart meter dataset, example workflow configurations, deployment artifacts, research prototype implementation, source code, and evaluation scripts, are publicly available through the Zenodo repository at: https://zenodo.org/records/21187749.

Supplementary Figure 1: Flowchart of the workflow orchestration engine. The diagram illustrates the sequence of operations performed by the workflow orchestration engine, including data acquisition, preprocessing, workflow execution, machine learning-based validation, decision generation, and result reporting for automated low-voltage acceptance testing.Please click here to download this file.

Supplementary Figure 2: Cloud–edge architecture for low-voltage acceptance automation. The architecture illustrates the interaction between edge devices and cloud services. Electrical measurements collected from smart meters, SCADA systems, and IoT devices are processed at the edge for preprocessing and real-time inference, then transmitted to the cloud for storage, analytics, model management, and visualization via an interactive monitoring dashboard.Please click here to download this file.

Discussion

The experimental evaluation demonstrated that the proposed workflow-oriented Low-Voltage (LV) Acceptance Automation Platform consistently outperformed the benchmark approaches in classification, forecasting, fault detection, operational decision latency, and scalability. These performance improvements resulted from the integration of advanced feature engineering, workflow orchestration, cloud-edge collaboration, and hybrid rule-based and machine learning decision-making rather than from the use of a single machine learning model. The findings are consistent with previous studies demonstrating that workflow-oriented automation and intelligent IoT architectures improve operational efficiency, interoperability, and decision support in industrial and smart grid applications^2,3,9,10,18.

The statistical analyses further strengthened the reliability of the experimental findings. Pairwise significance testing, one-way analysis of variance (ANOVA), confidence interval analysis, and Receiver Operating Characteristic (ROC) analysis confirmed that the proposed framework achieved statistically significant improvements over the benchmark methods while maintaining excellent classification capability across different decision thresholds^47,48,49. These statistical evaluations provide additional evidence that the observed performance improvements were not attributable to random variation.

The scalability and ablation studies further demonstrated the effectiveness of the proposed architecture under increasing computational workloads and different system configurations. The scalability analysis showed that the framework maintained lower processing times than the benchmark methods as the dataset size increased from 1,000–5,000 samples. Similarly, the ablation study confirmed that each major component contributed to the overall system performance. Feature engineering improved the representation of operational characteristics extracted from smart meter data, the intelligent decision module enhanced fault prediction and automated validation, workflow orchestration optimized task scheduling and execution, and cloud-edge collaboration reduced communication overhead and operational decision latency. These observations agree with previous reports highlighting the advantages of cloud-edge architectures and process orchestration for achieving scalable and low-latency industrial IoT systems^{9,15,19,20,21}.

Because the proposed framework operates within an IoT-enabled LV environment, cybersecurity and data privacy are important considerations for practical deployment. Secure communication between smart meters, edge devices, gateways, and cloud services can be achieved using Transport Layer Security (TLS)-enabled MQTT and HTTPS protocols. Role-based access control (RBAC) provides authentication and authorization for workflow management and system resources, whereas Advanced Encryption Standard (AES)-256 encryption protects operational data during transmission and storage. Audit logging and secure cloud-edge synchronization further support data integrity, confidentiality, and traceability throughout the acceptance workflow. These security mechanisms are consistent with current recommendations for secure Industrial Internet of Things (IIoT) and smart grid communication infrastructures^6,7,19,20,21.

The proposed framework also contributes to the development of intelligent power distribution systems by introducing a unified workflow-oriented architecture that integrates cloud-edge collaboration, workflow orchestration, feature engineering, and machine learning-based decision-making within a single automation platform. Unlike conventional IoT-based monitoring approaches that primarily focus on data acquisition and centralized processing^1,10,11,12, the proposed framework supports automated validation, intelligent fault detection, and process-driven decision-making. The scalability and ablation studies further demonstrate the advantages of modular intelligent architectures for future smart energy management and Industry 4.0 applications^3,9,14,15.

From a practical perspective, the proposed LV Acceptance Automation Platform enables real-time monitoring, automated validation, intelligent fault detection, and acceptance decision-making with minimal human intervention. The achieved operational decision latency of 31 ms and fault detection rate of 98.4% demonstrate the capability of the framework to support real-time industrial applications. Furthermore, the cloud-edge collaborative architecture reduces communication overhead while providing the scalability required to process data acquired from smart meters, distributed energy resources, and IoT-enabled devices. These capabilities align with current trends in smart grid automation and intelligent energy management systems^{18,19,20,21,27,29,30}.

Despite the promising results, several limitations should be acknowledged. The experimental evaluation was conducted using the Open LV Network & Smart Meter Dataset together with synthetic fault data because publicly available LV datasets do not provide comprehensive fault annotations. Consequently, the simulated fault scenarios and rule-based labels may not fully represent the diversity of real-world operating conditions. Furthermore, validation was performed using a single dataset, and practical deployment may be affected by communication constraints, sensor errors, and the computational limitations of edge devices operating under heterogeneous network conditions. Although cybersecurity mechanisms were considered within the proposed architecture, their implementation and evaluation were beyond the scope of this study. Future work will therefore focus on validating the framework using independent real-world datasets, diverse LV network topologies, and field deployment scenarios. Additional research will investigate adaptive intelligent energy management, explainable artificial intelligence, digital twin-assisted monitoring, and enhanced cloud-edge collaboration to further improve the robustness, scalability, and interpretability of intelligent LV acceptance automation systems^40,41.

Matériaux

Liste des matériaux utilisés dans cet article

Nom	Entreprise	Numéro de catalogue	Commentaires
Apache Spark	Apache Software Foundation	Version 3.4+	Analyses de données à grande échelle
Apache Superset	Apache Software Foundation	Version 3.x	Tableau de bord analytique
Docker Engine	Docker Inc.	Version 24.x	Déploiement d'applications
Eclipse Mosquitto MQTT Broker	Eclipse Foundation	Version 2.x	Échange de données
EdgeX Foundry (version Jakarta ou ultérieure)	LF Edge (Linux Foundation)	Version Jakarta / Geneva	Gestion des dispositifs périphériques
Flask / FastAPI	Pallets Projects / Sebastián Ramírez	Flask 2.3+ / FastAPI 0.100+	Intégration d'API backend
Grafana	Grafana Labs	Version 10.x	Visualisation et surveillance
Passerelle IoT industrielle	Advantech / Siemens	ECU-1251 / SIMATIC IOT2040	Communication capteur-vers-cloud
Capteurs IoT (capteurs de tension/courant)	Texas Instruments / Analog Devices	INA219 / ACS712	Surveillance en temps réel du réseau
Kit de développement Jetson Nano	NVIDIA Corporation	945-13450-0000-100	Inférence d'intelligence artificielle en périphérie
Kubernetes	Cloud Native Computing Foundation (CNCF)	Version 1.27+	Évolutivité des flux de travail
Modèle LSTM (Keras/TensorFlow)	Google (TensorFlow/Keras)	Inclus dans TF 2.12+	Prévision et prédiction de charge
Module de communication par ligne électrique (PLC)	STMicroelectronics	ST7580	Communication pour réseau intelligent
Plotly Dash	Plotly Inc.	Version 2.x	Visualisation interactive
Python 3.10	Python Software Foundation	Version 3.10.x	Traitement et analyse de données
PyTorch	Meta AI	Version 2.0+	Mise en œuvre de l'apprentissage profond
Algorithme de forêt aléatoire	Scikit-learn	Inclus dans la version 1.3+	Classification des défauts
Raspberry Pi 4 Modèle B (4 Go de RAM)	Raspberry Pi Foundation	RPI4-MODBP-4GB	Traitement en périphérie
React.js / Angular	Meta / Google	React 18.x / Angular 16+	Développement d'interface utilisateur
Module transceiver RS-485	Maxim Integrated (Analog Devices)	MAX485	Connectivité des dispositifs industriels
Scikit-learn	Développeurs de Scikit-learn	Version 1.3+	Modèles d'apprentissage automatique
Machine à vecteurs de support (SVM)	Scikit-learn	Inclus dans la version 1.3+	Classification et validation
TensorFlow	Google LLC	Version 2.12+	Entraînement de modèles
Twilio / Firebase Cloud Messaging	Twilio Inc. / Google	Non applicable	Alertes et notifications
Module Wi-Fi	Espressif Systems	ESP8266 / ESP32	Transmission de données
XGBoost	DMLC (Distributed ML Community)	Version 1.7+	Soutien intelligent à la prise de décision