Search

The mobile battery energy storage systems (MBESS) utilize flexibility in temporal and spatial to enhance smart grid resilience and economic benefits. Recently, the high penetration of renewable energy increases the volatility of electricity prices and gives MBESS an opportunity for price difference arbitrage. However, the strong randomness of both the traffic system and renewable energy leads to difficulty in achieving profit with acceptable risk. To address this problem, this paper proposes a risk-sensitive MBESS control framework based on safe deep reinforcement learning, which can constrain the risk under a certain level according to the company’s risk preference. The risk-estimation safe deep deterministic policy gradient (RE-SDDPG) algorithm is proposed to learn the optimal policy under the premise of lacking direct risk signals. Moreover, a hybrid risk estimation method is proposed to avoid local convergence caused by inaccurate estimation during the learning process. Last, a parameter-sharing method is applied to increase learning efficiency by sharing the Q networks’ parameters. The proposed methods are tested in the IEEE 30-bus system. The results show that the proposed method can keep the profit at a relatively high level while reducing the risk and increase learning efficiency compared with existing methods.

Applying large language models (LLMs) to modern power systems presents a promising avenue for enhancing decision-making and operational efficiency. However, this action may also incur potential security threats, which have not been fully recognized so far. To this end, this article analyzes potential threats incurred by applying LLMs to power systems, emphasizing the need for urgent research and development of countermeasures.

Developing the deep learning (DL) technique is a promising way to improve renewable energy forecasting accuracy and offset the negative impacts of renewable energy on the power system. However, the application of the DL technique brings novel cyberthreats to the renewable energy forecast, and its cybersecurity has not received enough attention in previous literatures. To fill the gap, the vulnerability of renewable energy forecasting is, among the first, studied in-depth in this article. First, a novel cyberattack named adversarial learning attack (ALA) is proposed. The ALA is achieved by tampering with the meteorological data obtained by online weather forecasts from external application programming interfaces to undermine the renewable energy forecasting performance, which jeopardizes the power system operation. Then, an iterative algorithm is proposed to solve the ALA-based optimization problem. As the DL model is involved as optimization constraints, the optimization problem is nonconvex and NP-hard, which is unable to be solved by traditional approaches. The proposed algorithm utilizes the proximal gradient descent principle and is effective in iteratively exploring the near-optimal solution. At last, the impact of the ALA strategy on the power system operation is assessed, which considers the economic loss incurred and the potential hazards. The feasibility and efficacy of the ALA strategy are validated by conducting comprehensive and extensive experiments on the IEEE 30-bus benchmarks. The simulation results reveal that the ALA is able to impose severe economic losses on the operation and even induces disastrous hazards, such as power system collapse.

Nowadays, with the wide installation of distributed energy resources and independent energy storage systems, prosumers as a new type of electricity market entity have emerged. Since numerous prosumers can significantly impact the carbon emission of the power grid, this paper proposes an improved carbon emission flow method for the power grid with prosumers. This method can accurately clarify the detailed distribution of electrical carbon emission flow in power grids. First, based on the power flow, prosumers’ impacts on the electrical carbon emission are quantified from three aspects that include the carbon emission sources, the network flow, and the indirect carbon emission individuals. Then, an improved power carbon emission flow model is proposed, in which the complex carbon emission intensity of prosumers is derived emphatically. Finally, case studies based on the IEEE 30-bus system verify the feasibility of the proposed method. This method provides a measurement basis for further research considering electrical carbon emissions.

Designing customized dynamic pricing is a promising way to incent consumers to adjust their daily energy consumption behaviors. It helps manage flexible demand response resources on peak load. However, it is insufficiently investigated in previous studies from the individual behavior perspective. To tackle the gap, this paper proposes a graph deep learning-based retail dynamic pricing mechanism. First, a graph attention network-based temporal price elasticity perceptron model is proposed. It explores a novel path to learn price elasticity by using graph deep learning, and can accurately assess consumers’ energy consumption behaviors under different prices. Then, to avoid unfair evaluation of demand response, two indexes are proposed as auxiliary measures to assess energy consumption behavior learning models. At last, a customized dynamic pricing model based on the temporal price elasticity perceptron model is proposed. It can develop consumer’s time-varying demand response potential. This potential is first defined in this paper to measure what potentials of shifting/curtailing energy during a period a consumer has. By the pricing, the consumer could be incented to engage in demand response. The numerical studies validate the feasibility and superiority of the proposed methods, meanwhile price risks from the price change can be hedged effectively.

Developing the deep learning (DL) technique is a promising way to enhance smart grid (SG) cybersecurity. However, previous DL methods require massive attack samples for cyberattack correlation learning, whilst the real-world SG is incapable of providing such a large dataset. Moreover, existing work commonly focuses on extracting temporal features from power grid data for cyberattack detection, while the spatial features are insufficiently investigated. To address these limitations, a spatiotemporal graph deep learning (STGDL)-based scheme is proposed to detect cyberattacks without requiring attack samples. First, the graph convolution and temporal gated convolution are orchestrated to extract spatiotemporal features jointly. Then, a quantile regression training strategy is adopted to give normally operational bounds of state variables in state estimation (SE). It gets rid of limitations on needing attack samples, and the state bounds can indicate cyberattack anomalies. At last, a super-resolution perception (SRP) network is proposed. The SRP network is able to reconstruct the high-frequent data of estimated states from low-frequent SE results, so as to improve the temporal learning ability in the STGDL model. The feasibility and effectiveness of the proposed scheme are validated by conducting comprehensive and extensive experiments on the IEEE 30-bus and 118-bus benchmarks.

The smart grid is an evolving critical infrastructure, which combines renewable energy and the most advanced information and communication technologies to provide more economic and secure power supply services. To cope with the intermittency of ever-increasing renewable energy and ensure the security of the smart grid, state estimation, which serves as a basic tool for understanding the true states of a smart grid, should be performed with high frequency. More complete system state data are needed to support high-frequency state estimation. The data completeness problem for smart grid state estimation is therefore studied in this paper. The problem of improving data completeness by recovering high-frequency data from low-frequency data is formulated as a super resolution perception (SRP) problem in this paper. A novel machine-learning-based SRP approach is thereafter proposed. The proposed method, namely the Super Resolution Perception Net for State Estimation (SRPNSE), consists of three steps: feature extraction, information completion, and data reconstruction. Case studies have demonstrated the effectiveness and value of the proposed SRPNSE approach in recovering high-frequency data from low-frequency data for the state estimation.

Modern power systems are rapidly evolving into complex cyber-physical systems. The increasingly complex interaction among different energy entities calls for a secure, efficient, and robust cyber infrastructure. As an emerging distributed computing technology, Blockchain provides a secure environment to support such interactions. This paper gives a prospective on using Blockchain as a secure, distributed cyber infrastructure for the future grid. Firstly, the basic principles of Blockchain and its state-of-the-art are introduced. Then, a Blockchain based smart grid cyber-physical infrastructure model is proposed. Afterwards, some promising application domains of Blockchain in future grids are presented. Following this, some potential challenges are discussed.

Static security assessment (SSA) is an important procedure to ensure the static security of the power system. Researches recently show that cyber-attacks might be a critical hazard to the secure and economic operations of the power system. In this paper, the influences of false data injection attack (FDIA) on the power system SSA are studied. FDIA is a major kind of cyber-attacks that can inject malicious data into meters, cause false state estimation results, and evade being detected by bad data detection. It is firstly shown that the SSA results could be manipulated by launching a successful FDIA, which can lead to incorrect or unnecessary corrective actions. Then, two kinds of targeted scenarios are proposed, i.e., fake secure signal attack and fake insecure signal attack. The former attack will deceive the system operator to believe that the system operates in a secure condition when it is actually not. The latter attack will deceive the system operator to make corrective actions, such as generator rescheduling, load shedding, etc. when it is unnecessary and costly. The implementation of the proposed analysis is validated with the IEEE-39 benchmark system.

Destroying image integrity in scientific papers may result in serious consequences. Inappropriate duplication and fabrication of images are two common misconducts in this aspect. The rapid development of artificial-intelligence technology has brought to us promising image-generation models that can produce realistic fake images. Here, we show that such advanced generative models threaten the publishing system in academia as they may be used to generate fake scientific images that cannot be effectively identified. We demonstrate the disturbing potential of these generative models in synthesizing fake images, plagiarizing existing images, and deliberately modifying images. It is very difficult to identify images generated by these models by visual inspection, image-forensic tools, and detection tools due to the unique paradigm of the generative models for processing images. This perspective reveals vast risks and arouses the vigilance of the scientific community on fake scientific images generated by artificial intelligence (AI) models.

This paper proposes an integrated optimization algorithm (IOA) designed for solving complicated optimization problems that are non-convex, non-differentiable, non-continuous, or computationally intensive. IOA is synthesized from 5 sub-algorithms: follower search, leader search, wanderer search, crossover search, and role learning. The follower search finds better solutions by tracing the leaders. The leader search refines current optimal solutions by approaching or deviating from the central point of the population and then executes a single-round coordinate descent. The wanderer search carries out comprehensive search space expansion. The crossover search generates offspring using solutions from superior parents. Role learning automates the process in which a search agent decides whether to become a follower or a wanderer. A global optima estimation framework (GOEF) is proposed to offer guidelines for designing an efficient optimization algorithm, and IOA is proved to attain global optima. A differentiable integrated optimization algorithm (DIOA) that extends gradient descent is put forward to train deep learning models. Empirical case studies conclude that IOA shows a much faster convergence speed and finds better solutions than the other 8 comparative algorithms based on 27 benchmark functions. IOA has also been applied to solve unit commitment problems in the power system and shows satisfactory results. A power line sub-image classification model based on a convolutional neural network (CNN) is optimized by DIOA. Compared with the pure gradient descent approach, DIOA converges significantly faster and obtains a high test set accuracy with much fewer training epochs. [ABSTRACT FROM AUTHOR]

In this paper, we present the problem formulation and methodology framework of Super Resolution Perception (SRP) on smart meter data. With the widespread use of smart meters, a massive amount of electricity consumption data can be obtained. Smart meter data is the basis of automated billing and pricing, appliance identification, demand response, etc. However, the provision of high-quality data may be expensive in many cases. In this paper, we propose a novel problem - the SRP problem as reconstructing high-quality data from unsatisfactory data in smart grids. Advanced generative models are then proposed to solve the problem. This technology makes it possible for empowering existing facilities without upgrading existing meters or deploying additional meters. We first mathematically formulate the SRP problem under the Maximum a Posteriori (MAP) estimation framework. The dataset namely Super Resolution Perception Dataset (SRPD) is designed for this problem and released. A case study is then presented, which performs SRP on smart meter data. A network namely Super Resolution Perception Convolutional Neural Network (SRPCNN) is proposed to generate high-frequency load data from low-frequency data. Experiments demonstrate that our SRP models can reconstruct high-frequency data effectively. Moreover, the reconstructed high-frequency data can lead to better appliance identification results. [ABSTRACT FROM AUTHOR]