Time-series forecasting with missing values remains a critical challenge across diverse domains. While Transformer-based models excel with complete data, they suffer from “attention sink” where attention mechanisms disproportionately focus on missing data points, creating a self-reinforcing feedback loop that degrades performance. To address this, we propose meta-enhanced attention (MeaTS), a novel end-to-end Transformer-based framework specifically designed for robust multivariate time-series forecasting with missing values. Our approach introduces two key innovations, first, an MeaTS mechanism that dynamically adjusts attention weights by suppressing focus on missing values while amplifying attention to observed data, effectively mitigating the attention sink problem; second, an extracting latent value module that transforms data with missing values into informative features through frequency-domain representations, enhancing data representation without explicit imputation. Extensive experiments demonstrate that MeaTS achieves a 19.86% improvement in mean absolute error compared to state-of-the-art models, such as SDformer, GinAR+, and BiTGraph.

With the increasing prevalence and evolvement of ongoing technologies in household smart meters, nonintrusive load monitoring (NILM) becomes a convenient and cost-effective solution for appliance-level energy monitoring and analysis. As a vital tool for more informed electricity usage management, NILM is naturally intersected with the emerging field of deep learning. However, the predominant focus in deep learning-based NILM research is on enhancing the structure of neural networks, giving little emphasize on the data quality problem which heavily influences the accuracy and robustness of NILM. To address this issue, this article analyses the point-type and pattern-type abnormal data that may affect the accuracy of NILM, and proposes a data anomaly detection method accordingly based on an enhanced cycle-consistent generative adversarial network, which can represent the characteristics of load series in a low-dimensional latent space. Furthermore, by this latent space, we present an anomaly calibration approach based on clustering and nearest neighbors approximation. Extensive experiments using the open data sets are designed to demonstrate the effectiveness of the proposed method in improving NILM accuracy in both on/off states identification and appliance-level load prediction.

Uncertainty sets (USs) based on historical data have been applied for accurately characterizing the uncertainty of renewable energy resource (RES) unit outputs in robust energy scheduling involving virtual power plants (VPPs). However, it remains highly challenging to develop scheduling solutions that optimally balance between security and economic efficiency and the lowest computational burden. This involves constructing the smallest possible linear-form US that encompasses RES uncertainty data with a minimum number of vertices. The present work addresses these challenges by developing a data-driven minimum-volume ellipsoid US (EUS) with flexible confidence levels. The number of vertices in the obtained EUS is reduced to improve the computational efficiency of the solution process by approximating the EUS using a hybrid polyhedron US (HPUS) composed of rectangular and diamond USs. Finally, a vertex-based column-and-constraint generation algorithm, which can avoid falling into locally optimal solutions, is designed to solve the robust VPP energy scheduling model with the HPUS. The effectiveness and superiority of the proposed US approach and algorithm are verified based on a practical VPP system in South China.

Hybrid ac/dc microgrids (HMGs) have emerged as a promising paradigm for integrating large numbers of inherently uncertain and correlated renewable energy sources (RESs). To address the uncertainty introduced by extensive RES integration, a quad-level energy management model is proposed for HMGs, incorporating a novel data-driven uncertainty set. Specifically, a pair convex hull uncertainty set (PCHUS) is developed with adjustable size, which utilizes a graph neural network to identify and exclude outliers in RES data. This approach provides trustworthy RES data at any given confidence level. Then, a quad-level energy management model is designed to determine the minimal-size PCHUS among all possible options, ensuring the least conservative solution, while maintaining robustness against RES fluctuations. Furthermore, a modified version of Taguchi’s orthogonal array testing (TOAT) method, termed quasi-TOAT, enhances the proposed solution algorithm. This modification enables parallel processing capabilities, significantly improving both the global optimum-seeking process and computational efficiency. To validate the proposed approach, the proposed uncertainty set and enhanced algorithm are compared against existing methods using a practical HMG case study. The results demonstrate the effectiveness and superiority of the proposed methodology in managing uncertainty within HMGs.

Privacy of user is becoming increasingly significant in constructing efficient multiagent energy management systems for multimicrogrid (MMG). As an emerging privacy-protection method, federated learning (FL) has been used to prevent data breaches in the MMG-related field. However, with the ever-growing participants, the underlying communication burden existing in FL is evident. Besides, since the neural network layers collectively determine an agent's performance, the possible difference in layer convergence speeds would cause the inconsistency problem, that is, the FL may degrade the convergence rate of those fast-convergent layers, which weakens the overall performance of the agent. To address these issues, a communication-efficient FL (CEFL) algorithm is proposed in this study. Considering the cooperative relationship among layers, a layer evaluation (LE) mechanism is developed in CEFL to evaluate layer contribution through the Shapley value (SV), a profit distribution approach for coalitions. In this way, only partial layers with the highest contributions are selected to be uploaded to the server. In addition, instead of average parameters aggregation, a communication-efficient parameter aggregation method is proposed in CEFL to update the parameters of the global model (GM), in which an aggregation model (AM) is developed to receive parameters for aggregation. The performance of the proposed CEFL is verified by the numerical analysis of MMGs with 3-8 MGs participating. Furthermore, experiments investigate the influence of the hyperparameter in the CEFL and also demonstrate performance improvements, compared with the other four state-of-the-art algorithms.

This paper proposes a distributionally robust optimal operation methodology to coordinate multi-energy interactions and facilitate the emission mitigation for multi-energy systems (MESs) with uncertainty couplings in electricity and carbon markets. A carbon recycling model is proposed to exploit the operational flexibility of multi-energy synergies to enhance economic profits of MES operators under market incentives. Then, a generalized cost model incorporating the lifetime cost of carbon capture and power-to-gas degradation is formulated to provide a quantitative analysis for the coordinated electricity and carbon trading. The co-movements of price fluctuations in electricity and carbon markets are explored through a tailored explainable neural network and uncertainty couplings in the markets are further revealed by a Clayton copula based joint probability distribution (PD) model of price prediction residuals. Moreover, a distributionally robust optimization method is formulated for the optimal coordinated operation of MESs to cope with uncertainties from interrelated fluctuating prices. Numerical studies corroborate the effectiveness and superiority of the proposed methodology in the enhancement of economic and environmental benefits.

Most of the existing signcryption schemes utilize a key generation center to generate pseudonyms without updating, and usually opt for bilinear pairing to design authentication schemes. The disadvantage is that these schemes not only incur heavy computation and communication overheads during information interaction, but also can not eliminate security risks arising from not updating pseudonyms. These limitations render them less effective for smart terminals (STs) with limited computation and communication resources in cyber-physical power systems. The main purpose of this article is to explore a streamlined signcryption scheme tailored for resource-limited STs. To achieve this, a dynamical pseudonym self-generation mechanism (DPSGM) is first introduced to prevent the source from being linked and protect privacy. In addition, a streamlined signcryption scheme is designed based on elliptic curve cryptography and certificateless cryptography, integrating seamlessly with DPSGM. This design significantly reduces computation and communication burdens during information interaction. Finally, a real experimental platform is established to demonstrate the feasibility and effectiveness of the proposed scheme. Visual interfaces show the entire secure interaction process and the resistance to attacks.

False data injection attacks (FDIAs) represent a significant threat to power grid cybersecurity, designed to manipulate crucial measurement data and thereby compromise the operation of power grids. This article proposes an ac FDIA method based on tensor principle component analysis (TPCA), requiring no prior knowledge of system parameters. The goal of the proposed approach is to produce false data that can break through the bad data detection (BDD) of realistic ac state estimation. Specifically, ac state estimation model is transformed into a tensor representation, encapsulating measurement variables, state variables, and system parameters as a combination of multiple tensor products. Following this, by formulating multiple measurement data into a tensor, TPCA is used to decompose the measurement data tensor to obtain a space of matrices. Subsequently, the vector of false data ensuring the stealthiness is produced by finding a rank-1 approximation of matrices in this space. Notably, the proposed method distinguishes itself from existing parameter-free FDIA methods by eschewing any simplification or approximation of ac state estimation model. Numerous cases in IEEE 5, 14, 57, 118, 300-bus, European 1354-bus, and Polish 3120-bus testing systems provide substantial evidence that the proposed approach can obtain higher attack successful rate. It achieves 99.3% attack successful rate on average against the common$\chi ^{2}$BDD with 0.9 confidence level. And compared with existing methods, the attack successful rate improves 4%, 2%, 13%, 11%, 10%, and 27% in these six systems, respectively.

Wind power prediction interval (WPPI) is the most common technique to represent wind power (WP) uncertainty. This article proposes a novel WPPI approach developed based on predictive density estimation (DE). Unlike most WPPI models in the literature, the proposed model does not need to solve a high-dimensional optimization problem for model training. It optimizes the WPPIs using a single control variable—the bandwidth (BW) of DE—and trains the model directly and noniteratively using the quantiles extracted from the WP predictive density. For predictive DE, a novel application-specific method has been developed based on generalized cross-entropy (GCE). A precise but straightforward technique is designed to determine the optimal BW that results in the optimal WPPIs. The original GCE-based DE problem is also transformed into a convex quadratic programming formulation that can be solved quickly and uniquely. The WPPI model is employed in a new hybrid deterministic/probabilistic WPP (HDPWP) framework. Different from the conventional HDPWP approach that constructs WPPIs based on the point prediction error, the proposed framework incorporates WP point prediction among the predictor variables in the WPPI model, thereby improving performance. The effectiveness of the proposed methods is confirmed through extensive simulations and comparisons using real-world WP generation datasets.

This article proposes a multilateral multienergy trading framework for synergetic hydrogen (H2) and electricity transactions among renewable-dominated hybrid charging stations (HCSs). In this framework, each autonomous HCS with various renewable energy resource (RES) endowment can harvest local renewables for internal green H2and electricity generation to simultaneously meet demands of electric vehicles (EVs) and hydrogen-powered vehicles (HVs) from the transportation network. The surplus electricity/H2production of the HCS is accommodated by external multilateral transactions to increase the additional profit. Besides, each HCS is modeled as a sustainable energy hub, and multiple hubs with multienergy transactions contribute toward a low-carbon energy-transport nexus. A partial differential equation model based on fluid dynamic theory is formed to capture the temporal and spatial dynamics of traffic flows for estimating the EV/HV loads at HCSs. Furthermore, a distributed multilateral pricing algorithm is developed to iteratively derive the optimal prices and quantities for transactive electricity and H2. Comparative studies corroborate the superiority of the proposed methodology on economic merits and RES accommodation.

Successful detection of false data injection attacks (FDIAs) and removal of state bias due to FDIAs are essential for ensuring secure power grids operation and control. This article first extends the approximate dc model of FDIA to a more general ac model that can handle both traditional and synchronized measurements. To automatically filter out the established FDIAs, we propose a state reconstruction scheme consisting of a contaminated state separation method, an enhanced bad data identification approach and a state recovery algorithm. In this scheme, a classifier is developed by aggregating a series of extreme learning machines (ELMs) to detect anomaly states caused by FDIAs. Gaussian random distribution and Latin hypercube sampling are adopted to initialize the input weights of base ELMs, which can provide more diversities to enhance the ensemble performance. Then, to identify the exact locations of the compromised measurements, a state forecasting-based bad data identification approach is proposed by exploiting the consistency between the forecasted and the received measurements. Finally, an effective state recovery algorithm applies quasi-Newton method and Armijo line search to address the possible system unobservable problem due to the removal of attacked measurements. Numerical tests on serval IEEE standard test systems verify the efficiency of the proposed FDIA model and state reconstruction scheme.

This article proposes a two-layer optimal scheduling strategy to handle the overvoltage problem in high photovoltaic (PV) power-penetrated distribution networks. The voltage regulators can be classified as the power utility and PV owners, which are referred to as stakeholders. The proposed scheduling strategy includes autonomous optimization layer and coordination optimization layer. In the autonomous optimization layer, a min-max robust game model and a mixed-integer second-order cone programming-based model are respectively proposed to minimize the operating costs of PV stakeholders and the power utility stakeholder. A parallel optimization is employed to solve the two models in the autonomous optimization layer. In the coordination optimization layer, a noncooperative game-based model is presented to coordinate scheduling solutions of each stakeholder. Finally, an actual 10 kV, 106-bus feeder in Zhejiang Province, China, and a modified IEEE 123-bus distribution system are employed to verify the feasibility and effectiveness of the proposed approach.

To tackle the challenges introduced by the fast-growing charging demand of electric vehicles (EVs), the power distribution systems (PDSs) and fast charging stations (FCSs) of EVs should be planned and operated in a more coordinated fashion. However, existing planning approaches generally aim to minimize investment costs in PDSs while ignoring the risk of worsening traffic conditions. To overcome this research gap, this article integrates the interests of traffic networks into PDS and FCS joint planning model to mitigate negative impacts on traffic conditions caused by installing FCSs. First, a novel microscopic method that is different from traditional assignment methods is proposed to simulate the influences of FCSs on traffic flows and EV charging loads. Then, a multiobjective joint planning model is developed to minimize both the planning costs and unbalanced traffic flows. A new bilayer Benders decomposition algorithm is designed to solve the proposed joint planning model. Numerical results on two practical systems in China validate the feasibility of our microscopic method by comparing the simulated results with real data. Compared with existing approaches, it is also demonstrated that the proposed joint planning approach helps to balance traffic flow assignments and relieve traffic congestion.

Extreme events can extensively damage power systems, causing customers to experience long-lasting outages. During such events, an electric vehicle (EV) can be used to directly power a house, i.e., vehicle-to-home (V2H). Specifically, the EV serves as a mobile energy storage system-running errands to “transport” energy from other places. Vehicle-to-grid (V2G) further allows cooperation among houses. It enables EV fleets to take turns running the errands so that sustained power supply is possible. Moreover, autonomous driving technology can also benefit system adequacy because the charging errands of EVs can be scheduled flexibly without being bonded to human activities. An emergency power supply strategy featuring scheduled EV charging errands as introduced above is proposed. It answers the questions whether and to what extent a system can survive an extended period of outage with the use of EVs only. An optimization problem is formulated with the purpose of maximizing the supply adequacy of the isolated system during the outage period. Both V2H and V2G scenarios are considered in the problem formulation, as well as self-driving capability. The complex optimization problems are solved with genetic algorithm. It is significant to find from the case study that the proposed strategy is able to fully restoring an islanded system when V2G and self-driving EVs are implemented.

Recently developed data acquisition equipment and data processing methods have ignited the possibility of power system online sensitivity identification (OSI). Despite the existing OSI algorithms, practical issues such as data collinearity and the noise effect on the identification algorithm must be considered to realize OSI in real-power systems. In this study, the negative and positive aspects of noise to OSI are first studied. Then, under the data collinearity condition and by making use of the positive aspects of noise, a noise-assisted ensemble regression method is proposed to simultaneously solve the data collinearity problem and manage the negative aspects of noise. Moreover, the proposed method is proven equivalent to one of the most effective measures, the norm-2 regularization method, to address the collinearity problem, and therefore provides satisfactory OSI results. The proposed method is tested in an 8-generator 36-node system with original operations data from a real-power system, and the results validate its effectiveness.

Measurement sensors installed in the smart transmission system can acquire big data for electromechanical dynamics monitoring. The time-series data obtained carry information of instantaneous relationship of system oscillation modes with respect to operating conditions. To extract this information, this paper proposes a parallel processed online supervised learning algorithm called k-nearest neighbors “locally weighted linear regression” (KNN-LWLR), which is an extensive combination of two famous machine-learning algorithms: 1) the KNN learning; and 2) LWLR learning. Its mathematical derivation, implementation, parameter tuning, and application to electromechanical oscillation mode prediction are first described. The proposed algorithm is then validated based on an 8-generator 36-node system with the real operations data.

In the electricity market environment, it is very important for generation companies (GENCOs) to make the optimal mid-term generation operation planning (MTGOP) which includes the trading strategies in the spot market and the contract market as well as the suitable unit maintenance scheduling (UMS). In making the decision of MTGOP, GENCOs are subject to risk due to uncertain factors, and hence should manage the inevitable risk rationally. Given this background, a new MTGOP model is first developed for a GENCO as a price taker so as to maximize its profit and minimize its risk measured by the Conditional Value-at-Risk (CVaR). In this model, the bilateral physical contracts are taken into consideration, together with the transmission congestion and the operation constraints of generating units. Then, a solving method is given by integrating the Genetic Algorithm and the Monte Carlo method. Finally, a numerical example is used to show the features of the proposed method.

In this work, PSO is applied to solve power flow problem. For efficient search, some parameters in PSO are investigated and parameter sensitivity analyses are carried out to find the optimum value for the relevant parameters. We further recommend a set of optimal PSO settings applied in Two-phase Particle Swarm Optimization in tackling power flow problem. Results show remarkable improvement in comparison to original PSO and Constrained Genetic Algorithm Power Flow (CGAPF).