You are accessing a machine-readable page. In order to be human-readable, please install an RSS reader. Contact online >>
You are accessing a machine-readable page. In order to be human-readable, please install an RSS reader.
All articles published by MDPI are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. For articles published under an open access Creative Common CC BY license, any part of the article may be reused without permission provided that the original article is clearly cited. For more information, please refer to https://
Feature papers represent the most advanced research with significant potential for high impact in the field. A Feature Paper should be a substantial original Article that involves several techniques or approaches, provides an outlook for future research directions and describes possible research applications.
Feature papers are submitted upon individual invitation or recommendation by the scientific editors and must receive positive feedback from the reviewers.
Editor''s Choice articles are based on recommendations by the scientific editors of MDPI journals from around the world. Editors select a small number of articles recently published in the journal that they believe will be particularly interesting to readers, or important in the respective research area. The aim is to provide a snapshot of some of the most exciting work published in the various research areas of the journal.
Visit our dedicated information section to learn more about MDPI.
Minh, Q.N.; Nguyen, V.-H.; Quy, V.K.; Ngoc, L.A.; Chehri, A.; Jeon, G. Edge Computing for IoT-Enabled Smart Grid: The Future of Energy. Energies 2022, 15, 6140. https://doi /10.3390/en15176140
Minh QN, Nguyen V-H, Quy VK, Ngoc LA, Chehri A, Jeon G. Edge Computing for IoT-Enabled Smart Grid: The Future of Energy. Energies. 2022; 15(17):6140. https://doi /10.3390/en15176140
Minh, Quy Nguyen, Van-Hau Nguyen, Vu Khanh Quy, Le Anh Ngoc, Abdellah Chehri, and Gwanggil Jeon. 2022. "Edge Computing for IoT-Enabled Smart Grid: The Future of Energy" Energies 15, no. 17: 6140. https://doi /10.3390/en15176140
Minh, Q. N., Nguyen, V. -H., Quy, V. K., Ngoc, L. A., Chehri, A., & Jeon, G. (2022). Edge Computing for IoT-Enabled Smart Grid: The Future of Energy. Energies, 15(17), 6140. https://doi /10.3390/en15176140
Subscribe to receive issue release notifications and newsletters from MDPI journals
Thank you for visiting nature . You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.
The excellent, good, fair, and poor coordinate points represent the general performance of different methods in various dimensions. Our proposed federated split learning integrates the advantages of federated learning and split learning methods, achieving exceptional performance across all dimensions.
We first present a concise overview of the proposed end-edge-cloud framework for intellectualizing smart meters. As shown in Fig.2, the framework consists of a hierarchy with three levels: smart meters, edge servers, and a cloud server. The proposed framework is capable of collaboratively training the model deployed on different entities with distributed data in a privacy-enhancing manner to address the challenges posed by the resource constraints and insufficient data of individual smart meters. To enable accurate on-device load forecasting with memory, computation, and communication efficiency, our framework incorporates three critical phases, namely, model splitting, model training, and model aggregation.
In the model splitting phase, the cloud server determines an efficiency-optimal model split ratio for each smart meter and edge server pair. This aims to minimize the training time while avoiding memory overflow on smart meters. Consequently, the model is split into three components: a feature extractor, a feature processor, and a regressor. The feature extractor and regressor involve private raw data and thus are deployed on smart meters, while the feature processor requires complex computations and thus is deployed on edge servers. In this way, most of the resource burden of the model training is transferred to edge servers.
In the model training phase, the smart meters and edge servers collaboratively train the model deployed on them. We introduce a small auxiliary network as an extra regressor on smart meters to update the end- and edge-side models in parallel. This parallelism significantly reduces the computation time and communication overhead. To enhance the model accuracy, a knowledge distillation-based mechanism is employed to guarantee objective consistency between the two split models throughout the training process.
In the model aggregation phase, the cloud server and the edge servers aggregate the trained models in a hierarchical way. We first adopt a hardware-aware clustering algorithm to designate smart meters with similar training times to the same edge server. This allows the models of intra-cluster smart meters to be synchronously aggregated by edge servers. Subsequently, the aggregated models of each edge server can be asynchronously uploaded to update the global model via the cloud server. This two-stage semi-asynchronous approach effectively reduces the delay time without compromising accuracy by combining the benefits of the synchronous and asynchronous methods.
We develop a federated split learning approach under this framework, which mainly incorporates three phases: (1) model splitting, in which the cloud server splits the large model and assigns a small portion to smart meters and a larger portion to the edge servers; (2) model training, in which multiple smart meters collaborate with edge servers to train the complete model; (3) model aggregation, in which the trained models are hierarchically aggregated by the edge servers and the cloud server to update the global model.
a Schematic of the hardware platform. The established platform instantiates the proposed end-edge-cloud framework for comprehensive experiments. The memory-constrained smart meter cannot match the requirement of numerous variable parameters and massive amounts of constantly collected data for model training. b Comparison of forecasting accuracy versus memory usage on smart meters for our method and benchmark methods with different model sizes. The average forecasting accuracy with 95% confidence intervals is presented with five independent experiments. Source data are provided as a Source Data file.
Each hidden layer is considered a candidate split layer. The split layers that yield the best efficiency are annotated. The hidden layers contained in the feature extractor, feature processor, and regressor after the optimal splitting are indicated with different colors. The total training times under four distinct hardware configurations when choosing different split layers are provided. The stacked histograms represent the measured times for communication, forward propagation of the edge server and smart meter, and parallel backward propagation, arranged from bottom to top. Source data are provided as a Source Data file.
We compare the model performance in terms of accuracy, training time, and communication per round when the parallelism and knowledge distillation mechanisms are removed. The mean accuracy with 95% confidence intervals is presented with five independent experiments. Source data are provided as a Source Data file.
We compare the model performance in terms of the accuracy, total training time, and communication overhead of the proposed method with the, synchronous, asynchronous, and semi-asynchronous model aggregation methods. Source data are provided as a Source Data file.
About Edge computing smart grid
As the photovoltaic (PV) industry continues to evolve, advancements in Edge computing smart grid have become critical to optimizing the utilization of renewable energy sources. From innovative battery technologies to intelligent energy management systems, these solutions are transforming the way we store and distribute solar-generated electricity.
When you're looking for the latest and most efficient Edge computing smart grid for your PV project, our website offers a comprehensive selection of cutting-edge products designed to meet your specific requirements. Whether you're a renewable energy developer, utility company, or commercial enterprise looking to reduce your carbon footprint, we have the solutions to help you harness the full potential of solar energy.
By interacting with our online customer service, you'll gain a deep understanding of the various Edge computing smart grid featured in our extensive catalog, such as high-efficiency storage batteries and intelligent energy management systems, and how they work together to provide a stable and reliable power supply for your PV projects.
