In cyber-physical power systems, state estimation (SE) serves as a critical function for operational monitoring but is increasingly vulnerable to functional failures induced by stealthy external attacks. To overcome the limitations of traditional attack detection methods for SE, particularly their heavy reliance on prior attack models and static measurement infrastructures, this paper proposes a robust SE model that proactively introduces dynamic spatiotemporal measurement uncertainty (DSTMU) to detect stealthy false data injection attacks (FDIAs) without requiring an explicit prior attack model, thus improving the resilience and security of power system operations. First, to disrupt the attacker's static perception of the measurement configuration, a robust SE model with structural uncertainty and adversarial resilience is constructed by dynamically reconfiguring the measurement sampling pattern via spatial selection and temporal weighting matrices, leveraging the inherent redundancy of hybrid SCADA and WAMS measurements. Subsequently, a consistency-based detection index, the random measurement selection consistency index (RMSCI), is designed to quantify the deviations in SE results caused by varying measurement configurations. The statistical characteristics of RMSCI are analytically derived under normal and adversarial conditions, verifying its sensitivity to stealthy attacks. Furthermore, an offline robust detection-oriented optimization model is formulated, jointly optimizing the measurement selection strategies and detection thresholds. A Benders decomposition-based algorithm is employed to achieve efficient offline solution convergence for the detection-oriented deployment problem. Finally, simulation results demonstrate that the proposed method can effectively detect FDIAs of varying intensities without requiring additional hardware or external detection modules.

With the deep integration of power systems into cyber-physical systems (CPSs), the widespread deployment of measurement terminals and high-frequency information interactions have significantly expanded the attack surface. State estimation (SE), as a critical function, is increasingly vulnerable to severe cyber threats. To expose the security vulnerabilities of current state estimation processes, a covert data tampering attack method without relying on prior knowledge is proposed in this paper, addressing the limitations of previous attack methods, which generally face challenges in acquiring system models or lack theoretical guarantees for covertness. The core innovation lies in an adversarial attack framework that integrates an adversarial autoencoder (AAE) and a generative adversarial network (GAN), along with a bidirectional SE agent model designed to eliminate explicit reliance on accurate mechanistic models. Within this framework, an unsupervised generator deeply coupled with physical constraints is designed to jointly optimize attack strength and covertness through a composite loss function. The effectiveness of the proposed method is demonstrated through case studies, where high-threat, low-detectability attack vectors are generated in real time, misleading state estimation results while successfully evading conventional grid security protection mechanisms.

In practical applications, the degradation behavior of lithium-ion batteries exhibits significant differences due to variations in operating conditions. Meanwhile, the scarcity of labeled data poses considerable challenges for capacity prediction in terms of both accuracy and generalization. To address these issues, this article proposes a cross-domain semisupervised capacity prediction framework that integrates multigranularity feature modeling with a confidence controlled pseudolabel selection mechanism. Specifically, the proposed method enhances the model’s ability to capture the granularity of nonlinear degradation trends in battery capacity, thereby improving prediction accuracy and stability. In addition, a pseudolabel learning strategy based on confidence filtering and stagewise regulation is designed to dynamically guide high-quality pseudolabels in the target domain into training, effectively reducing the risk of noisy label propagation. Experiments conducted on eight tasks across two heterogeneous battery datasets demonstrate R$^{2}$improvements of 1.3%–8.7% and Mean Absolute Error (MAE) reductions of 38%–80%, validating the practical potential of the proposed method under complex degradation scenarios.

State estimation (SE) is vital for secure power system operation, but remains susceptible to stealthy false data injection attacks (FDIAs). Existing detection methods are primarily designed using prior attack knowledge, which limits their adaptability to unknown threats. This article introduces the concept of controllable uncertainty into SE, where uncertainty is actively regulated at inference time rather than passively induced by stochastic training effects, and proposes an attack-resilient SE model that enables active defense through an integrated estimation-detection-feedback mechanism. In the estimation stage, a spatiotemporal LSTM-GNN-based model equipped with Monte Carlo dropout executes multisample perturbation passes on identical inputs, whereas physics-consistency constraints enforce power-flow feasibility. In the detection stage, a detection index coupling mean shift and uncertainty expansion is introduced, with thresholds obtained via statistical calibration and perturbation-response bounds to ensure detectability without excessive false alarms. In the feedback stage, the dropout rate and the sampling density are adapted online in response to the detection statistics, amplifying attack signatures under anomalies and attenuating perturbations in normal scenarios to preserve estimation accuracy. Case studies on the standard test systems demonstrate consistently higher detection rates, lower false-alarm rates, and online latency compatible with operational requirements against single-snapshot, temporally optimal, and spatiotemporally coordinated FDIAs, without additional hardware investment. The results indicate that integrating physics consistency with actively controllable uncertainty offers a practical pathway toward enhancing the functional safety and resilience of SE.

With the widespread proliferation of electric vehicles (EVs), optimizing the operation of EV charging stations (EVCSs) has become increasingly important. Strategic charging prices can influence both revenue and service efficiency, while differentiated pricing for different EVs can further help mitigate overstay issues. Moreover, under the concept of the peer-to-peer (P2P) sharing economy, energy and carbon allowance trading among EVCSs presents a significant opportunity to reduce both operational costs and carbon emissions. However, limited research has examined such interactions and the specific economic and environmental impacts of joint energy and carbon (E&C) trading in multi-EVCS systems. In this paper, we investigate a joint differentiated pricing and E&C trading problem for multiple EVCSs, aiming to maximize both economic and environmental benefits. Specifically, we first formulate a total revenue-maximization problem that incorporates anxiety-differentiated pricing and P2P E&C trading among multiple interconnected EVCSs. We then propose an operational algorithm to solve the problem based on Nash bargaining and the alternating direction method of multipliers, which can protect privacy and mitigate communication barriers among EVCSs. Simulation results demonstrate that the proposed algorithm can simultaneously improve revenue and achieve low-carbon goals.

The coordinated operation of grid-interactive buildings contributes to creating a more resilient and reliable power grid. However, existing studies fail to identify the demand changes of each building resulting from their coordinated participation in providing grid services, which affects the economic compensation of each building and its willingness to coordinate. In this article, we investigate an optimal coordinated operation problem for grid-interactive residential buildings (GRBs) while considering generation capacity services and economic compensation for participating GRBs. Specifically, we first formulate two optimization problems to capture the different objectives of GRBs during non-service periods and grid-service periods, respectively. Then, we develop a physically consistent neural network (PCNN)-assisted hierarchical model predictive control (HMPC)-based GRB energy management algorithm to solve the optimization problem during non-service periods. Next, we propose a coordinated operation algorithm to solve the optimization problem during grid-service periods based on PCNN-assisted HMPC and rule-assisted binary search. By comparing the initial solutions from the proposed energy management algorithm with the final solutions generated by the proposed coordination algorithm, the demand changes of each GRB during service periods can be identified. Simulation results indicate that the proposed coordination algorithm achieves up to 37.8114% lower energy costs and 82.1459% better grid service performance than benchmarks while maintaining high thermal comfort. Note to Practitioners—Buildings with distributed energy resources (e.g., solar generation, energy storage) and flexible loads (e.g., heating, ventilation, and air conditioning (HVAC) systems) have significant potential to provide grid services, such as voltage support, frequency regulation, and power peak reduction. Since a single residential building contributes minimally to service quality, multi-building coordination through a trusted third party is necessary. However, since participation in providing grid services may affect occupant comfort and building energy costs, the demand change of each residential building should be identified so that the corresponding economic compensation can be calculated, which is a key factor for the successful deployment of such grid-interactive residential buildings (GRBs). To this end, we develop an optimal energy management algorithm for each residential building during non-service periods, which aims to minimize building energy cost while maintaining high occupant comfort. Based on the developed energy management algorithm, a coordinated operation algorithm for service periods is further proposed to limit the peak demand below a value predetermined by the system operator. By comparing the initial decisions from the energy management algorithm with the final decisions generated by the proposed coordination algorithm, we can identify the demand change of each building during service periods. Numerical results demonstrate that the proposed coordinated operation algorithm can help participating GRBs reduce energy costs and enhance service performance for power grids, with negligible sacrifice to occupant comfort.

This article aims to address the formation control issue of the unknown nonaffine nonlinear heterogeneous multiagent system (MAS) considering formation tracking accuracy and computational cost. A novel dynamic prescribed boundary-based event-triggered mechanism is proposed first to flexibly adjust the emphasis on these two indicators, and applied to data modeling and controller design simultaneously to reduce their computational cost. On one hand, an observer-based pseudo gradient estimation algorithm is designed under event-triggered framework for model reconfiguration with only input/output data of system rather than mathematical dynamics. On the other hand, an event-triggered constrained control strategy is developed with several modules to cope with complex scenarios. Concretely, a data-driven anti-windup compensator is designed in case of input constraint, and an improved prescribed performance-based fractional order terminal sliding mode controller is explored for enhancement of the formation tracking accuracy and robustness of the controlled MAS with rigorous stability analysis. Both numerical simulation and hard-in-the-loop experiment on distributed energy storage systems are performed to attest the efficacy of the proposed formation control strategy.

Battery energy storage systems (BESS) are essential for modern energy management, supporting renewable integration and grid stability. However, fault diagnosis for BESS requires extensive manual network tuning. To overcome this, we introduce a zero-shot neural architecture search approach for BESS fault diagnosis. First, the neural network is broken down into piecewise linear functions, and the Rademacher complexity is calculated for this class of functions. To prevent batch normalization (BN) layers from repeatedly scaling the Rademacher complexity and invalidating network comparisons, the Rademacher complexity is approximated using the variance of the BN layers. Finally, the selected models are then compressed via 8-bit quantization to facilitate deployment on mobile devices. This approach achieves 99.42% accuracy in just 0.51 GPU h, significantly reducing model search time without needing pretrained models. We validate this method on a self-developed BESS platform featuring a battery management system and custom mobile app, accessible online.

This article presents a comprehensive analysis of the limitations associated with single ES in regulating CL voltage, specifically highlighting their restricted adjustment range and suboptimal performance in high-power applications. To address these challenges, a novel parallel configuration of ESs is proposed for the first time, with an in-depth examination of its design principles and critical technical issues. To overcome the energy supply limitations inherent in traditional ES systems, the study integrates PV systems and BESS, replacing the conventional assumption of an ideal dc power source. This integration establishes a PV/BESS model that not only enhances the utilization efficiency of renewable energy but also ensures effective stabilization of the dc bus voltage. Under diverse disturbances, including solar irradiance fluctuations and microgrid voltage variations, the proposed parallel PV/BESS energy storage system achieves seamless coordinated operation via MPC, substantially expanding the CL voltage regulation range. However, disparities in internal parameters and switching states among parallel ESs may induce significant circulating currents, posing a threat to system stability. To mitigate this issue, a multiagent-based MPC approach is introduced. This method incorporates a circulating current suppression term into the cost function alongside the CL voltage regulation objective, ensuring balanced currents distribution across all units while significantly enhancing system stability and coordination. Simulation and experimental results demonstrate the effectiveness of the proposed multiagent MPC strategy, confirming its capability to significantly improve the stability and performance of the parallel PV/BESS ESs system.

The shift towards transportation electrification, marked by the rising use of electric vehicles (EVs) and the development of fast charging stations (FCS), plays a crucial role in transport decarbonization initiatives. To optimize the rollout of FCS and set appropriate charging service fees (CSF)-a process referred to as the coupled FCS multi-stage bi-level operation problem (FCS-MBOP)-is essential for improving both investment and operational efficiency within the integrated power distribution and transportation network (CPTN). For operators, it's not only necessary to adapt to short-term fluctuations within the environment but also to swiftly respond to changes in the FCS layout resulting from various long-term investment decisions. To address this complexity, we introduce a dual-timescale evolutionary assist deep reinforcement learning framework, which includes two specialized agents with distinct functions: an investment agent (planner) and an operational agent (operator). The planner focuses on annual investments, evolving long-term strategies that weigh social benefits against investment costs through the use of a genetic algorithm (GA). In contrast, the operator acts on an hourly basis, fine-tuning CSF to alleviate traffic congestion and minimize the social costs, while taking into account the planner's feasible investment decisions. Leveraging the integrated capabilities of a graph neural network (GNN), long-short-term memory (LSTM), and attention mechanisms, our framework's agents are adept at extracting both temporal and spatial features and facilitating the transfer of experiences across different investment stages. Empirical evidence underscores the effectiveness of our approach, showcasing its ability to surpass conventional methodologies in delivering high-quality solutions.

Sequential decision making is an important part of robotic problems that is receiving unprecedented attention from both academia and industry. Recently, Deep Reinforcement Learning (DRL) has shown its promising capabilities in decision making problems. However, traditional DRL algorithms directly operate in the space of low-level actions, when it is applied in the domain of robotics, it can easily result in an exponential growth of computational complexity and suffer from the “curse of dimensionality”, becoming less efficient as the dimensionality of the environment increases. To address this issue, a novel DRL hyper-heuristic approach is proposed in this paper. The proposed approach is tailored to align with a problem taken from a real-world competition by taking advantage of well-developed low-level heuristic actions in order to narrow the search space and speed up the convergence. This fundamental contribution is a significant step forward from earlier approaches that directly exploit the entire low-level action domain. A state augmentation scheme and a novel reward design are utilized to further improve the performance of the proposed method. Moreover, a Real-to-Sim based training framework is developed to reduce the cost of acquiring real-time data and improve the robustness of agent’s decision-making model. Numerous experimental results demonstrate our proposed method can achieve notable performance gains compared to both competitive DRL baselines and heuristic approaches of the same problem in both known environment and previously unseen scenarios.

Transportation electrification, involving large-scale integration of electric vehicles (EV) and fast charging stations (FCS), constitutes one of the key enablers toward decarbonization. Coordination of EV charging routes and demand through suitably designed price signals constitutes an imperative step in secure and economic operation of the coupled transportation network (TN) and power distribution network (PDN). In this work, we model the noncooperative pricing game of self-interested FCSs, taking into account the complex interactions between the EV users and the coupled operation of TN and PND. The uncertainties stemming from the EV users' cost elasticity and their travel energy requirements are encapsulated in the modeling of the TN, while the power flows in the PDN are coordinated considering the penetration of renewable energy sources. A modified multiagent proximal policy optimization method is developed to solve the pricing game. It employs an attention mechanism to selectively incorporate agents' representative information for estimating the Q-values. As such, it not only mitigates the nonstationary effect without exploding the input of the centralized critic but also safeguards the business confidentiality of FCSs. Moreover, a sequential updating scheme is used to ensure policy monotonic improvement and a Bayesian inference technique is adopted to enhance the robustness of the pricing strategy. Case studies on a large-scale test CTPN system reveal that the proposed method facilitates sufficient competition among FCSs, which is able to drive down the average charging prices for EV users. It also smooths out the spatial distribution of EV charging demands, which reduces the traffic congestions in the TN while enhancing the wind absorption and cost efficiency of the PDN.

Digitalization is one of the key drivers for energy system transformation. The advances in communication technologies and measurement devices render available a large amount of operational data and enable the centralization of such data storage and processing. The greater access to data opens up new opportunities for a more efficient and decentralized management of the energy system. At the distribution level of the energy system, local electricity markets (LEMs) provide new degrees of flexibility by trading and balancing the energy locally and offering ancillary services to the wider transmission and distribution system operators. Maximizing the grid impact from this flexibility calls for novel data analytics and artificial intelligence techniques to enhance the system’s security and reduce the energy costs of local prosumers. At the same time, however, relying on data-based approaches increases the risk of cyberattacks, and robust countermeasures are, therefore, needed as an integral aspect of digitalization efforts. This article discusses the key role of centralized data analytics to fully benefit from the advantages of LEMs in terms of system’s security enhancement and energy costs’ reduction. Data-driven paradigms are investigated that allow for flexibility from decentralized markets, mitigate the physical security risks, and devise defensive strategies shielding the system from cyber threats.

Peer-to-peer (P2P) energy trading has emerged as a promising market paradigm toward maximizing the value of distributed energy resources (DERs) for electricity prosumers, by enabling direct energy trading among them. However, state-of-the-art P2P mechanisms either fail to adequately incentivize prosumers to participate, prevent prosumers from accessing the highest achievable monetary benefits, or suffer severely from the curse of dimensionality. This article proposes two computationally efficient mechanisms to construct a stable grand coalition of prosumers participating in P2P trading, founded on cooperative game-theoretic principles. The first one involves a benefit distribution scheme inspired by the core tâtonnement process while the second involves a novel pricing mechanism based on the solution of a single linear program. The performance of the proposed mechanisms is validated against state-of-the-art mechanisms through numerous case studies using real-world data. The results demonstrate that the proposed mechanisms exhibit superior computational performance than the nucleolus and are superior to the rest of the examined mechanisms in incentivizing prosumers to remain in the grand coalition.

The problem of real-time autonomous energy management is an application area that is receiving unprecedented attention from consumers, governments, academia, and industry. This paper showcases the first application of deep reinforcement learning (DRL) to real-time autonomous energy management for a multi-carrier energy system. The proposed approach is tailored to align with the nature of the energy management problem by posing it in multi-dimensional continuous state and action spaces, in order to coordinate power flows between different energy devices, and to adequately capture the synergistic effect of couplings between different energy carriers. This fundamental contribution is a significant step forward from earlier approaches that only sought to control the power output of a single device and neglected the demand-supply coupling of different energy carriers. Case studies on a real-world scenario demonstrate that the proposed method significantly outperforms existing DRL methods as well as model-based control approaches in achieving the lowest energy cost and yielding a representation of energy management policies that adapt to system uncertainties.