Showing papers on "Smart grid published in 2022"
TL;DR: In this paper , a study on data-driven probabilistic machine learning (ML) techniques and their real-time applications to smart energy systems and networks was conducted to highlight the urgency of this area of research.
Abstract: The current trend indicates that energy demand and supply will eventually be controlled by autonomous software that optimizes decision-making and energy distribution operations. New state-of-the-art machine learning (ML) technologies are integral in optimizing decision-making in energy distribution networks and systems. This study was conducted on data-driven probabilistic ML techniques and their real-time applications to smart energy systems and networks to highlight the urgency of this area of research. This study focused on two key areas: i) the use of ML in core energy technologies and ii) the use cases of ML for energy distribution utilities. The core energy technologies include the use of ML in advanced energy materials, energy systems and storage devices, energy efficiency, smart energy material manufacturing in the smart grid paradigm, strategic energy planning, integration of renewable energy, and big data analytics in the smart grid environment. The investigated ML area in energy distribution systems includes energy consumption and price forecasting, the merit order of energy price forecasting, and the consumer lifetime value. Cybersecurity topics for power delivery and utilization, grid edge systems and distributed energy resources, power transmission, and distribution systems are also briefly studied. The primary goal of this work was to identify common issues useful in future studies on ML for smooth energy distribution operations. This study was concluded with many energy perspectives on significant opportunities and challenges. It is noted that if the smart ML automation is used in its targeting energy systems, the utility sector and energy industry could potentially save from $237 billion up to $813 billion. • A study on data-driven probabilistic machine learning (ML) in sustainable smart energy/smart energy systems is conducted. • The use of probabilistic ML in core energy technologies are briefly studied. • The ML techniques play a key role in integrating thermal, electric, large-scale renewable energy resources and fuel gird.A variety of tools for implementing ML in energy systems control, efficient management, and operations are discussed. • Recent key developments of ML, its challenges, and state-of-art future research opportunities are briefly described.
349 citations
TL;DR: The role of electric vehicles in energy systems will be crucial over the upcoming years due to their environmental-friendly nature and ability to mitigate/absorb excess power from renewable energy sources as mentioned in this paper .
Abstract: The role of electric vehicles (EVs) in energy systems will be crucial over the upcoming years due to their environmental-friendly nature and ability to mitigate/absorb excess power from renewable energy sources. Currently, a significant focus is given to EV smart charging (EVSC) solutions by researchers and industries around the globe to suitably meet the EVs' charging demand while overcoming their negative impacts on the power grid. Therefore, effective EVSC strategies and technologies are required to address such challenges. This review paper outlines the benefits and challenges of the EVSC procedure from different points of view. The role of EV aggregator in EVSC, charging methods and objectives, and required infrastructure for implementing EVSC are discussed. The study also deals with ancillary services provided by EVSC and EVs' load forecasting approaches. Moreover, the EVSC integrated energy systems, including homes, buildings, integrated energy systems, etc., are reviewed, followed by the smart green charging solutions to enhance the environmental benefit of EVs. The literature review shows the efficiency of EVSC in reducing charging costs by 30 %, grid operational costs by 10 %, and renewable curtailment by 40 %. The study gives key findings and recommendations which can be helpful for researchers and policymakers.
200 citations
TL;DR: In this paper , the authors comprehensively review smart grid cyber-physical and cyber security systems, standard protocols, and challenges, and provide a deep understanding of the cyber security system and standards and proposed direction for future research in smart grid system applications.
194 citations
TL;DR: In this paper , a secure federated deep learning based FDIA detection method was proposed by combining Transformer, federated learning and Paillier cryptosystem, which utilizes the data from all nodes to collaboratively train a detection model while preserving data privacy.
Abstract: As an important cyber-physical system (CPS), smart grid is highly vulnerable to cyber attacks. Amongst various types of attacks, false data injection attack (FDIA) proves to be one of the top-priority cyber-related issues and has received increasing attention in recent years. However, so far little attention has been paid to privacy preservation issues in the detection of FDIAs in smart grids. Inspired by federated learning, a FDIA detection method based on secure federated deep learning is proposed in this paper by combining Transformer, federated learning and Paillier cryptosystem. The Transformer, as a detector deployed in edge nodes, delves deep into the connection between individual electrical quantities by using its multi-head self-attention mechanism. By using federated learning framework, our approach utilizes the data from all nodes to collaboratively train a detection model while preserving data privacy by keeping the data locally during training. To improve the security of federated learning, a secure federated learning scheme is designed by combing Paillier cryptosystem with federated learning. Through extensive experiments on the IEEE 14-bus and 118-bus test systems, the effectiveness and superiority of the proposed method are verified.
172 citations
TL;DR: In this article , the authors present an assessment framework that combines all the three methods in a single model to evaluate their synergistic effects on wind integration and network reliability, and show that the proposed combination of methods reduce system dispatch, load curtailment and wind curtailment costs the most when compared to any combinations with fewer methods or using each method in isolation.
153 citations
TL;DR: The challenges of next-generation smart-grids as it relate to the integration of AI, IoT and 5G for better smart grid architecture are discussed and possible solutions to some of the challenges and standards to support this novel trend are proposed.
Abstract: Smartgrid is a paradigm that was introduced into the conventional electricity network to enhance the way generation, transmission, and distribution networks interrelate. It involves the use of Information and Communication Technology (ICT) and other solution in fault and intrusion detection, mere monitoring of energy generation, transmission, and distribution. However, on one hand, the actual and earlier smartgrid, do not integrate more advanced features such as automatic decision making, security, scalability, self-healing and awareness, real-time monitoring, cross-layer compatibility, etc. On the other hand, the emergence of the digitalization of the communication infrastructure to support the economic sector which among them are energy generation and distribution grid with Artificial Intelligence (AI) and large-scale Machine to Machine (M2M) communication. With the future Massive Internet of Things (MIoT) as one of the pillars of 5G/6G network factory, it is the enabler to support the next generation smart grid by providing the needed platform that integrates, in addition to the communication infrastructure, the AI and IoT support, providing a multitenant system. This paper aim at presenting a comprehensive review of next smart grid research trends and technological background, discuss a futuristic next-generation smart grid driven by artificial intelligence (AI) and leverage by IoT and 5G. In addition, it discusses the challenges of next-generation smart-grids as it relate to the integration of AI, IoT and 5G for better smart grid architecture. Also, proffers possible solutions to some of the challenges and standards to support this novel trend. A corresponding future work will dwell on the implementation of the discussed integration of AI, IoT and 5G for next-generation smart grid, using Matlab, NS2/NS3, Open-daylight and Mininet as soft tools and compare with related literature.
146 citations
TL;DR: In this article , the authors present a detailed overview regarding the evolution of smart grids in conjunction with the employment of IoT systems as well as the essential components of IoE for decarbonisation.
Abstract: To achieve low-carbon sustainable energy development, new technologies such as Internet of Energy (IoE), intelligent systems and Internet of Things (IoT) as well as distributed energy generations via smart grids (SG) are gaining attention. The interoperability between intelligent energy systems, realised through the web, enables automatic consumption optimisation and increases network efficiency and intelligent management. IoE is an intriguing topic in close connection with the IoT, communication systems, SG and electrical mobility that contributes to energy efficiency to achieve zero-carbon technologies and green environments. Furthermore, nowadays, the widespread growth and utilisation of processors for mining digital currency in homes and small warehouses are some other factors to be considered in terms of electric energy consumption and greenhouse gas emission. However, research on the use of the Internet for evaluating the misallocation of energy and the effect it can have on CO2 emissions is often neglected. In this study, the authors present a detailed overview regarding the evolution of SG in conjunction with the employment of IoE systems as well as the essential components of IoE for decarbonisation. Also, mathematical models with simulation are provided to evaluate the role of IoE in reducing CO2 emission.
145 citations
TL;DR: Two novel strategies for determining the bilateral trading preferences of households participating in a fully Peer-to-Peer (P2P) local energy market are proposed: the first matches between surplus power supply and demand of participants, while the second is based on the distance between them in the network.
Abstract: This paper proposes two novel strategies for determining the bilateral trading preferences of households participating in a fully Peer-to-Peer (P2P) local energy market. The first strategy matches between surplus power supply and demand of participants, while the second is based on the distance between them in the network. The impact of bilateral trading preferences on the price and amount of energy traded is assessed for the two strategies. A decentralized fully P2P energy trading market is developed to generate the results in a day-ahead setting. After that, a permissioned blockchain-smart contract platform is used for the implementation of the decentralized P2P trading market on a digital platform. Actual data from a residential neighborhood in the Netherlands, with different varieties of distributed energy resources, is used for the simulations. Results show that in the two strategies, the energy procurement cost and grid interaction of all participants in P2P trading are reduced compared to a baseline scenario. The total amount of P2P energy traded is found to be higher when the trading preferences are based on distance, which could also be considered as a proxy for energy efficiency in the network by encouraging P2P trading among nearby households. However, the P2P trading prices in this strategy are found to be lower. Further, a comparison is made between two scenarios: with and without electric heating in households. Although the electrification of heating reduces the total amount of P2P energy trading, its impact on the trading prices is found to be limited.
134 citations
TL;DR: In this article , a framework was developed for the potential implementation of big data analytics for smart grids and renewable energy power utilities, and a five-step approach was proposed for predicting the smart grid stability by using five different machine learning methods.
Abstract: The application of big data in the energy sector is considered as one of the main elements of Energy Internet. Crucial and promising challenges exist especially with the integration of renewable energy sources and smart grids. The ability to collect data and to properly use it for better decision-making is a key feature; in this work, the benefits and challenges of implementing big data analytics for renewable energy power stations are addressed. A framework was developed for the potential implementation of big data analytics for smart grids and renewable energy power utilities. A five-step approach is proposed for predicting the smart grid stability by using five different machine learning methods. Data from a decentralized smart grid data system consisting of 60,000 instances and 12 attributes was used to predict the stability of the system through three different machine learning methods. The results of fitting the penalized linear regression model show an accuracy of 96% for the model implemented using 70% of the data as a training set. Using the random forest tree model has shown 84% accuracy, and the decision tree model has shown 78% accuracy. Both the convolutional neural network model and the gradient boosted decision tree model yielded 87% for the classification model. The main limitation of this work is that the amount of data available in the dataset is considered relatively small for big data analytics; however the cloud computing and real-time event analysis provided was suitable for big data analytics framework. Future research should include bigger datasets with variety of renewable energy sources and demand across more countries.
130 citations
TL;DR: In this article , a new framework for the scheduling of microgrids and distribution feeder reconfiguration is presented, taking into account the uncertainties due to the load demand, market price, and renewable power generation.
126 citations
TL;DR: In this paper , the authors proposed federated learning for load forecasting with smart meter data, which enables training a single model with all participating smart meters without the need to share local data.
TL;DR: The architecture and infrastructure of IoT-enabled smart grids are reviewed; major challenges and security issues regarding their implementation are focused on; and advanced solutions and technologies are highlighted that can help IoT- enabled smart grids be more resilient and secure in overcoming existing cyber and physical attacks.
Abstract: Swift population growth and rising demand for energy in the 21st century have resulted in considerable efforts to make the electrical grid more intelligent and responsive to accommodate consumers’ needs better while enhancing the reliability and efficiency of modern power systems. Internet of Things (IoT) has appeared as one of the enabling technologies for smart energy grids by delivering abundant cutting-edge solutions in various domains, including critical infrastructures. As IoT-enabled devices continue to flourish, one of the major challenges is security issues, since IoT devices are connected through the Internet, thus making the smart grids vulnerable to a diverse range of cyberattacks. Given the possible cascading consequences of shutting down a power system, a cyberattack on a smart grid would have disastrous implications for the stability of all grid-connected infrastructures. Most of the gadgets in our homes, workplaces, hospitals, and on trains require electricity to run. Therefore, the entire grid is subject to cyberattacks when a single device is hacked. Such attacks on power supplies may bring entire cities to a standstill, resulting in massive economic losses. As a result, security is an important element to address before the large-scale deployment of IoT-based devices in energy systems. In this report, first, we review the architecture and infrastructure of IoT-enabled smart grids; then, we focus on major challenges and security issues regarding their implementation. Lastly, as the main outcome of this study, we highlight the advanced solutions and technologies that can help IoT-enabled smart grids be more resilient and secure in overcoming existing cyber and physical attacks. In this regard, in the future, the broad implementation of cutting-edge secure and data transmission systems based on blockchain techniques is necessary to safeguard the entire electrical grid against cyber-physical adversaries.
TL;DR: Big data for energy analytics, digital twins in smart grid modeling, virtual power plants with Metaverse, and green IoT are the major vital recommendations that are discussed in this study for future enhancement.
Abstract: The United Nations’ sustainable development goals have emphasized implementing sustainability to ensure environmental security for the future. Affordable energy, clean energy, and innovation in infrastructure are the relevant sustainable development goals that are applied to the energy sector. At present, digital technologies have a significant capability to realize the target of sustainability in energy. With this motivation, the study aims to discuss the significance of different digital technologies such as the Internet of Things (IoT), artificial intelligence (AI), edge computing, blockchain, and big data and their implementation in the different stages of energy such as generation, distribution, transmission, smart grid, and energy trading. The study also discusses the different architecture that has been implemented by previous studies for smart grid computing. Additionally, we addressed IoT-based microgrids, IoT services in electrical equipment, and blockchain-based energy trading. Finally, the article discusses the challenges and recommendations for the effective implementation of digital technologies in the energy sector for meeting sustainability. Big data for energy analytics, digital twins in smart grid modeling, virtual power plants with Metaverse, and green IoT are the major vital recommendations that are discussed in this study for future enhancement.
TL;DR: In this article , the authors provide an extensive overview on the system configurations, interface topologies, marketing, and future perspectives in integrating EVs as virtual power plants, under the headings of stand-alone, grid-connected, transitional, and grid-supported operations.
Abstract: Global factors such as energy consumption and environmental issues encourage the utilization of electric vehicles (EVs) as alternative energy sources besides transportation. Recently, the development of virtual power plants integrated with clean energy sources has also enhanced the role of EVs in the transportation industry. Vehicle-grid integration (VGI) provides a practical and economical solution to improve energy sustainability and feed consumers on the user side. Although technical developments in the field show that the energy sector supports the effective use of EVs in stationary applications, the research studies confirm that scientific and industrial developments continue to improve the performance of using EVs as virtual power plants. However, a comprehensive study is needed to demonstrate the concepts, interfacing, and marketing of virtual power plants integrated with EVs for researchers and scientists working in this field. To this end, the current study aims to provide an extensive overview on the system configurations, interface topologies, marketing, and future perspectives in integrating EVs as virtual power plants. In this context, the integration concepts of VGI are investigated under the headings of stand-alone, grid-connected, transitional, and grid-supported operations. Then, VGI topologies are examined in terms of energy generation/storage units used in EVs, single-stage/two-stage/hybrid-multi-stage based systems, and grid-connection types & parameters. In the following section, the research projects and marketing values based on a large number of target data are introduced to show the current status of the VGI field. Lastly, future aspects, including charging strategies, intelligent technologies, and technical issues, are addressed and clarified.
TL;DR: In this paper , the authors present the challenges associated with V2G on the power grid and vehicle batteries, as well as their possible solutions, and highlight the research gap across the V2Gs domain.
Abstract: The gradual shift towards cleaner and green energy sources requires the application of electric vehicles (EVs) as the mainstream transportation platform. The application of vehicle-to-grid (V2G) shows promise in optimizing the power demand, shaping the load variation, and increasing the sustainability of smart grids. However, no comprehensive paper has been compiled regarding the of operation of V2G and types, current ratings and types of EV in sells market, policies relevant to V2G and business model, and the implementation difficulties and current procedures used to cope with problems. This work better represents the current challenges and prospects in V2G implementation worldwide and highlights the research gap across the V2G domain. The research starts with the opportunities of V2G and required policies and business models adopted in recent years, followed by an overview of the V2G technology; then, the challenges associated with V2G on the power grid and vehicle batteries; and finally, their possible solutions. This investigation highlighted a few significant challenges, which involve a lack of a concrete V2G business model, lack of stakeholders and government incentives, the excessive burden on EV batteries during V2G, the deficiency of proper bidirectional battery charger units and standards and test beds, the injection of harmonics voltage and current to the power grid, and the possibility of uneconomical and unscheduled V2G practices. Recent research and international agency reports are revised to provide possible solutions to these bottlenecks and, in places, the requirements for additional research. The promise of V2G could be colossal, but the scheme first requires tremendous collaboration, funding, and technology maturation.
TL;DR: The future grid refers to the next generation of the electrical grid, which will enable smart integration of conventional, renewable, and distributed power generation, energy storage, transmission and distribution, and demand management as mentioned in this paper .
Abstract: Future grid refers to the next generation of the electrical grid, which will enable smart integration of conventional, renewable, and distributed power generation, energy storage, transmission and distribution, and demand management [...]
TL;DR: In this article , the authors combine different deep learning algorithms with edge computing to analyze and process distributed renewable energy generation and consumer power data in smart microgrid to improve the efficiency of information transmission and processing in power systems.
Abstract: Smart Grid 2.0 is the energy Internet based on advanced metering infrastructure and distributed systems that require an instantaneous two-way flow of energy information. Edge computing benefits from its proximity to the servers and edge nodes of the smart grid distributed systems, which can provide efficient and low latency information transmission to the smart grid. With the massive number of Internet of Things being used, the amount of real-time power usage information generated by that represents a huge challenge for edge computing. To improve the efficiency of information transmission and processing in power systems, this article combines different deep learning algorithms with edge computing to analyze and process distributed renewable energy generation and consumer power data in smart microgrid. Experiments on two real-world datasets from China and Belgium show that the proposed framework can obtain satisfactory prediction accuracy compared to existing approaches.
TL;DR: In this article , transfer learning has been proposed as a promising solution to alleviate the issues of traditional machine learning algorithms, such as they might not perform as expected, take much time in training, or do not have enough input data to generalize well.
TL;DR: This work performs a comprehensive survey of edge computing for IoT-enabled smart grid systems and hopes that these study results will contribute important guidelines for in-depth research in the field of smart grids and green energy in the future.
Abstract: The explosive development of electrical engineering in the early 19th century marked the birth of the 2nd industrial revolution, with the use of electrical energy in place of steam power, as well as changing the history of human development. The versatility of electricity allows people to apply it to a multitude of fields such as transportation, heat applications, lighting, telecommunications, and computers. Nowadays, with the breakout development of science and technology, electric energy sources are formed by many different technologies such as hydroelectricity, solar power, wind power, coal power, etc. These energy sources are connected to form grid systems to transmit electricity to cities, businesses and homes for life and work. Electrical energy today has become the backbone of all modern technologies. To ensure the safe, reliable and energy-efficient operation of the grid, a wide range of grid management applications have been proposed. However, a significant challenge for monitoring and controlling grids is service response time. In recent times, to solve this problem, smart grid management applications based on IoT and edge computing have been proposed. In this work, we perform a comprehensive survey of edge computing for IoT-enabled smart grid systems. In addition, recent smart grid frameworks based on IoT and edge computing are discussed, important requirements are presented, and the open issues and challenges are indicated. We believe that in the Internet of Things era, the smart grid will be the future of energy. We hope that these study results will contribute important guidelines for in-depth research in the field of smart grids and green energy in the future.
TL;DR: In this paper , the authors discuss AI/ML algorithms that can help in developing energy efficient, secured and effective IoT network operations and services, and highlight application domains, including smart healthcare, smart agriculture, smart transportation, smart grid and smart industry that can operate efficiently and securely.
Abstract: The evolution of the wireless network systems over decades has been providing new services to the users with the help of innovative network and device technologies. In recent times, the 5G network systems are about to be deployed which creates the opportunity to realize massive connectivity with high throughput, low latency, high energy efficiency and security. It also focuses on providing massive Internet of Things (IoT) network connectivity as well as services for good health, large-scale agricultural and industrial production, intelligent traffic control and electricity generation, transmission and distribution systems. However, the ever-increasing number of user devices is directing the researchers towards beyond 5G systems to allocate these user devices with higher bandwidth. Researches on the 6G wireless network systems have already begun to provide higher bandwidth availability for densely connected larger network devices with QoS surety. Researchers are leveraging artificial intelligence (AI)/machine learning (ML) for enhancing future IoT network operations and services. This paper attempts to discuss AI/ML algorithms that can help in developing energy efficient, secured and effective IoT network operations and services. In particular, our article concentrates on the major issues and factors that influence the design of the communication systems for future IoT with the integration of AI/ML. It also highlights application domains, including smart healthcare, smart agriculture, smart transportation, smart grid and smart industry that can operate efficiently and securely. Finally, this paper ends with the discussion on future research scopes with these algorithms in addressing the open issues of the future IoT network systems.
TL;DR: In this paper , the authors designed a competitive market consisting of prosumers and retailers such that all prosumers (as buyers and sellers) and retailers conduct peer-to-peer energy trading, and a novel decentralized approach called primal-dual subgradient algorithm (PDSGA) is used to clear the designed market without third-party involvement or disclosure of players' private information.
TL;DR: This paper proposes a threat modeling framework and review the nature of cyber-physical attacks to understand their characteristics and impacts on the smart grid’s control and physical systems, and examines the existing threats detection and defense capabilities.
Abstract: The smart grid (SG), regarded as the complex cyber-physical ecosystem of infrastructures, orchestrates advanced communication, computation, and control technologies to interact with the physical environment. Due to the high rewards that threats to the grid can realize, adversaries can mount complex cyber-attacks such as advanced persistent threats-based and coordinated attacks to cause operational malfunctions and power outages in the worst scenarios: The latter of which was reflected in the Ukrainian power grid attack. Despite widespread research on smart grid security, the impact of targeted attacks on control and power systems is anecdotal. This article reviews the smart grid security from collaborative factors, emphasizing the situational awareness (SA). Specifically, we propose a threat modeling framework and review the nature of cyber-physical attacks to understand their characteristics and impacts on the smart grid’s control and physical systems. We examine the existing threats detection and defense capabilities, such as intrusion detection systems (IDSs), moving target defense (MTD), and co-simulation techniques, along with discussing the impact of attacks through situational awareness and power system metrics. We discuss the human factor aspects for power system operators in analyzing the impacts of cyber-attacks. Finally, we investigate the research challenges with key research gaps to shed light on future research directions.
TL;DR: In this paper , the authors present an overview of the latest research of EV charging stations and highlight some important issues and challenges in power architectures design, energy storage techniques, control strategies of micro-grid, and energy management optimization.
TL;DR: An innovative differential privacy (DP) compliant algorithm is developed to ensure that the data from consumer's smart meters are protected and provides privacy preservation in line with the consumer's preferences and does not lead to significant cost or loss increases for the energy retailer.
Abstract: The use of data from residential smart meters can help in the management and control of distribution grids. This provides significant benefits to electricity retailers as well as distribution system operators but raises important questions related to the privacy of consumers' information. In this article, an innovative differential privacy (DP) compliant algorithm is developed to ensure that the data from consumer's smart meters are protected. The effects of this novel algorithm on the operation of the distribution grid are thoroughly investigated not only from a consumer's electricity bill point of view but also from a power systems point of view. This method allows for an empirical investigation into the losses, power quality issues, and extra costs that such a privacy-preserving mechanism may introduce to the system. In addition, severalcost allocation mechanisms based on the cooperative game theory are used to ensure that the extra costs are divided among the participants in a fair, efficient, and equitable manner. Overall, the comprehensive results show that the approach provides privacy preservation in line with the consumer's preferences and does not lead to significant cost or loss increases for the energy retailer. In addition, the novel algorithm is computationally efficient and performs very well with a large number of consumers, thus demonstrating its scalability.
1 Jul 2022
TL;DR: In this article , a comprehensive review in the recent advances of the FDI attacks, with particular emphasis on adversarial models, attack targets, and impacts on the Smart Grid infrastructure is presented.
Abstract: Smart Grid is organically growing over the centrally controlled power system and becoming a massively interconnected cyber–physical system with advanced technologies of fast communication and intelligence (such as Internet of Things, smart meters, and intelligent electronic devices). While the convergence of a significant number of cyber–physical elements has enabled the Smart Grid to be far more efficient and competitive in addressing the growing global energy challenges, it has also introduced a large number of vulnerabilities in the cyber–physical space culminating in violations of data availability, integrity, and confidentiality. Recently, false data injection (FDI) has become one of the most critical types of cyberattacks, and appears to be a focal point of interest for both research and industry. To this end, this paper presents a comprehensive review in the recent advances of the FDI attacks, with particular emphasis on adversarial models, attack targets, and impacts on the Smart Grid infrastructure. This review paper aims to provide a thorough understanding of the incumbent threats affecting the entire spectrum of the Smart Grid. Related literature are analyzed and compared in terms of their theoretical and practical implications to the Smart Grid cybersecurity. In conclusion, a vast range of technical limitations of existing false data attack research is identified, and a number of future research directions is recommended.
TL;DR: In this paper , the authors proposed a novel privacy-preserving federated learning framework for energy theft detection, namely, FedDetect, in which each detection station (DTS) can only observe data from local consumers, which can use a local differential privacy scheme to process their data to preserve privacy.
Abstract: In smart grids, a major challenge is how to effectively utilize consumers’ energy consumption data while preserving security and privacy. In this article, we tackle this challenging issue and focus on energy theft detection, which is very important for smart grids. Specifically, we note that most existing energy theft detection schemes are centralized, which may be unscalable, and more importantly, may be very difficult to protect data privacy. To address this issue, we propose a novel privacy-preserving federated learning framework for energy theft detection, namely, FedDetect. In our framework, we consider a federated learning system that consists of a data center (DC), a control center (CC), and multiple detection stations. In this system, each detection station (DTS) can only observe data from local consumers, which can use a local differential privacy (LDP) scheme to process their data to preserve privacy. To facilitate the training of the model, we design a secure protocol so that detection stations can send encrypted training parameters to the CC and the DC, which then use homomorphic encryption to calculate the aggregated parameters and return updated model parameters to detection stations. In our study, we prove the security of the proposed protocol with solid security analysis. To detect energy theft, we design a deep learning model based on the state-of-the-art temporal convolutional network (TCN). Finally, we conduct extensive data-driven experiments using a real-energy consumption data set. The experimental results demonstrate that the proposed federated learning framework can achieve high accuracy of detection with a smaller computation overhead.
TL;DR: In this article , the authors present a rigorous review of blockchain implementations with the cyber security perception and energy data protections in smart grids, and describe the major security issues of smart grid scenarios that big data and blockchain can solve.
Abstract: The smart grid idea was implemented as a modern interpretation of the traditional power grid to find out the most efficient way to combine renewable energy and storage technologies. Throughout this way, big data and the Internet always provide a revolutionary solution for ensuring that electrical energy linked intelligent grid, also known as the energy Internet. The blockchain has some significant features, making it an applicable technology for smart grid standards to solve the security issues and trust challenges. This study will present a rigorous review of blockchain implementations with the cyber security perception and energy data protections in smart grids. As a result, we describe the major security issues of smart grid scenarios that big data and blockchain can solve. Then, we identify a variety of recent blockchain-based research works published in various literature and discuss security concerns on smart grid systems. We also discuss numerous similar practical designs, experiments, and items that have recently been developed. Finally, we go through some of the most important research problems and possible directions for using blockchain to address smart grid security concerns.
TL;DR: In this paper , the authors discuss and investigate the opportunities, challenges, and technologies of EVs in a V2G connecting system and provide potential recommendations for future research directions to solve the existing research gaps and issues.
TL;DR: This work designs an optimal communication and computational resource allocation method for this cloud-edge based smart grid fault detection system that can maximize the processing throughput of the system and improve resource utilization while satisfying the data transmission and processing latency requirements.
Abstract: Real-time smart grid monitoring is critical to enhancing resiliency and operational efficiency of power equipment. Cloud-based and edge-based fault detection systems integrating deep learning have been proposed recently to monitor the grid in real time. However, state-of-the-art cloud-based detection may require uploading a large amount of data and suffer from long network delay, while edge-based schemes do not adequately consider the detection requirement and thus cannot provide flexible and optimal performance. To solve these problems, we study a cloud-edge based hybrid smart grid fault detection system. Embedded devices are placed at the edge of the monitored equipment with several lightweight neural networks for fault detection. Considering limited communication resources, relatively low computation capabilities of edge devices, and different monitoring accuracies supported by these neural networks, we design an optimal communication and computational resource allocation method for this cloud-edge based smart grid fault detection system. Our method can maximize the processing throughput of the system and improve resource utilization while satisfying the data transmission and processing latency requirements. Extensive simulations are conducted and the results show the superiority of the proposed scheme over comparison schemes. We have also prototyped this system and verified its feasibility and performance in real-world scenarios.