Recent self-supervised pre-training methods for object detection often rely on generic object proposals for localization and semantic feature learning for classification, but they yield limited improvements when applied to Detection Transformers (DETR) due to a lack of architectural alignment. Hence, we propose an elegant and versatile self-supervised framework tailored for DETR-like models called Distance-aware Multi-view Contrastive Learning (DisCo DETR). DisCo DETR enhances localization and semantic features through two core components. (i) Distance-aware Multi-view Object Query Fusion explicitly guides object queries to focus on spatially close objects across views, stabilizing training and improving localization accuracy. (ii) Contrastive Learning for DETR uses native bipartite matching to identify positive output pairs across views and pull them closer, enhancing semantic features discrimination with no extra matching. DisCo DETR can be seamlessly integrated into DETR-like models and achieves SOTA transfer performance on PASCAL VOC and COCO benchmarks across multiple variants.

The research on home energy management systems (HEMSs) has attracted wide attention because of the development trend of urban smart buildings. However, coordinating various homes is a nontrivial task due to uncertainties regarding renewable energy, user behavior, and the concern of privacy disclosure. The complex properties of household appliances further put forward requirements for the decision-making procedure. To solve these, this article proposes a novel federated transfer framework based on a teacher–student learning paradigm for the energy optimization process. The pretrained model based on an open-source building environment is introduced to assist the learning procedure under a cross-domain adaption mechanism, which avoids the time-consuming learning process from scratch. Considering household appliance discrepancies, a hybrid proximal policy optimization method with discrete-continuous action space is proposed to schedule these devices optimally. Extensive experiments have demonstrated the effectiveness of our proposed method in terms of training performance, cost efficiency, and comfort level.

The operational optimization of integrated energy systems with high renewable energy penetration (IES-HREP) constitutes a complex systems engineering problem, primarily due to the absence of a well-defined cost model for renewable energy sources (RESs) generation and uncertainties affecting energy quality. To address these issues, this article proposes an entropy-based analysis and optimization framework to quantify RES uncertainty costs and system efficiency. First, an equivalent fuel (EF) cost model is introduced, integrating energy and information layers to quantify the cost of mitigating RES uncertainty. Building on this, entropy theory is employed to establish an information–energy quality coefficient (I-EQC) that evaluates RES energy quality by unifying thermodynamic and information entropy. In addition, a neurodynamics-based distributed algorithm is developed to perform multiobjective optimization for cost and exergy efficiency, enhancing computational speed while preserving data privacy. The simulation results demonstrate that the proposed framework reduces the cost by up to about 10% and improves the efficiency by up to about 5% compared to existing methods.

As the percentage of renewable energy in the Energy Internet (EI) gradually increases, how to deal with the uncertainty of renewable energy in the economic dispatch problem (EDP) becomes an important issue. This paper proposes a digital twin (DT) assisted economic dispatch strategy for EI with information entropy. First, we leverage the storage capacity of the DT and an extensive historical data set to provide a theoretical framework for quantifying uncertainty of renewable energy. Second, a renewable energy cost function based on the maximum entropy principle, confidence interval, and penalty factor is proposed to model the renewable energy resources considering the uncertainty. Further, we design a fully distributed Newton-surplus-based optimization algorithm. This algorithm achieves fast second-order convergence to ensure the real-time performance of the DT-assisted economic dispatch framework and overcome the asymmetry caused by the directed communication network. In addition, we give theoretical proof that the Newton-surplus-based algorithm can converge to the global optimal point. Finally, simulations validate the effectiveness of the proposed algorithm.Note to Practitioners—The essence of EDP is to minimize the total costs through optimal resource allocation while ensuring compliance with all operational constraints. With the increasing penetration of renewable energy resources, their strong stochasticity and uncertainty pose challenges to achieve reliable dispatch strategy. To address this issue, this paper presents the DT-assisted economic dispatch framework, model, and method to quantify the uncertainty of renewable energy resources and achieve distributed economic dispatch with fast convergence speed for EI. Our research is beneficial for practitioners to understand how to use the DT and information entropy to deal with the uncertain of renewable energy resources. The theory and simulation results demonstrate the correctness and effectiveness of the proposed method.

Interarea oscillations pose significant threats to the security and stability of power systems, and these oscillations have to be damped rapidly to prevent potential system failure. Our previous work introduced a deep reinforcement learning (DRL) strategy on top of the power oscillation damping (POD) control architecture using high-voltage direct current (HVdc) transmissions. This strategy effectively generated POD signals based on the wide-area information, thus modulating the transferred power to damp interarea oscillations. However, the performance degrades when there are significant changes in system structure or operating conditions, highlighting a general adaptability issue in DRL-based control schemes. To solve the issue, we propose a novel meta-evolution strategy framework that integrates both meta-strategy optimization (MSO) and evolutionary strategy (ES)-based DRL in this article. The ES algorithm has fewer hyperparameters that are relatively easy to tune than typical DRL algorithms and identifies the optimal policy quickly by exploring the policy parameter space through parallel computations. The MSO introduces a latent variable projecting the power system parameters under different operation conditions to ensure a fast and efficient adaption to unforeseen scenarios. A modified IEEE 39-bus system with HVdc transmission is studied to validate the performance and effectiveness of the proposed meta-strategy in damping interarea oscillations.

Nonintrusive load monitoring (NILM) aims to accurately identify appliance-level power consumption patterns solely based on the total household power signal, facilitating fine-grained management of smart grid demands. Previous monitoring methods have often focused on classifying time domain power signals or identifying appliance signatures in the frequency domain, lacking sufficient analysis of diverse, sparsely labeled data across different households in the time-frequency domain. We propose a novel model named frequency-division fusion scattering time-series transformer (FFSTT). Specifically, in addition to NILM task-driven token embedding, self-attention, and feed forward blocks, we innovatively employ dual-tree complex wavelet transform for time-frequency transformation of tokens. Distinct feature extraction methods are applied to low- and high-frequency components, respectively, to efficiently separate and learn the power consumption patterns of different appliances. Furthermore, to achieve effective domain transfer among households in different regions, we utilize a small amount of labeled data to perform low-rank fine-tuning on the pretrained FFSTT. Experiments conducted on the REDD and U.K.-DALE datasets confirm that the proposed model achieves state-of-the-art performance across distinct scenarios of available labeled data.

Although the P2P power transactions using the multiagent deep deterministic policy gradient (MADDPG) algorithm has been extensively studied, there are still challenges in privacy protection and training incentives. Furthermore, the stability and efficiency of the strategy decreases when dealing with nonindependent identically distribution (Non-IID) data from heterogeneous prosumers. Therefore, this article proposes a blockchain-enabled asynchronous federated learning-MADDPG (BEAFL-MADDPG) framework designed to enhance the training efficiency of heterogeneous prosumers while safeguarding data privacy. The framework includes a novel P2P energy trading model that facilitates energy trading amidst incomplete information while ensuring privacy assurances. In addition, a BEAFL-MADDPG algorithm is proposed, which accelerates training processes and enables parallel computation among agents. This algorithm enhances the efficiency of algorithm and empowers the training of diverse prosumers. Furthermore, a blockchain-enabled training mechanism and prosumer incentive scheme are proposed that not only encourage prosumer engagement in training but also ensure traceable transactions without the need for trust among participants. These mechanisms promote transparency and integrity, fostering a collaborative and secure environment for energy trading. Simulation results demonstrate that the framework achieves peak load reduction through optimized P2P trading, maintains computation efficiency across discount rates, and ensures secure transactions via blockchain-based incentives. These practical benefits support scalable and sustainable community microgrid operations.

Subsynchronous oscillations (SSOs) induced by the integration of high renewable energy penetration have significantly impacted the operation of power systems. This article proposed an enhanced matrix pencil method (MPM) for online monitoring of SSO using synchrophasors. To address the issue of eigenvalues of complex-domain matrix pencil not satisfying the conjugate frequency constraints of the synchrophasors, the complex Hankel matrix of synchrophasors is transferred to the field of real numbers. This improvement can shorten the data window of parameter identification to 200 ms while maintaining the computational efficiency of MPM. In addition, to ensure the identification accuracy by fully utilizing the information of complex-domain synchrophasors, the feasibility of constructing a new real-domain Hankel matrix with the combination of the separate real and imaginary parts of the complex Hankel matrix is proved. Compared with the existing MPM-based methods, the proposed enhanced MPM achieves better accuracy for parameter identification of SSOs while significantly reducing the computational burden in practical applications.

Communication network failure, e.g., persistent packet loss, may considerably affect the safe and stable operation of smart grids. This may degrade the performance of various components and applications, including energy management and economic dispatch. We propose a switched surplus-based distributed security dispatch approach to cope with the persistent packet loss under an unreliable communication network environment. First, we jointly consider the packet loss sequence and the dynamic triggering sequence to define actual affected periods caused by the persistent packet loss. Then, we outline an incentive scheme, integrate primal-dual analysis and eigenvalue perturbation theory to design the switched surplus-based distributed security dispatch algorithm. Further, we design a dynamic triggering mechanism that enables the proposed algorithm to dynamically switch to different modes according to the change in network state. With those components, the proposed method offers strong robustness against persistent packet loss. In addition, we provide the convergence and optimality proofs of the algorithm. Finally, simulation results are provided to validate the proposed method and to demonstrate its effectiveness.

Icing monitoring system within internet of things is developed to provide multimodal data for assessing the degree of icing on transmission lines. Nevertheless, existing methods relying solely on either sensor data or images demonstrate limited precision and inferior fault tolerance. This paper proposes a correlation-based multimodal feature fusion approach to integrate both sensor data and imaging data, thereby enhancing the monitoring of icing severity on transmission lines and addressing the aforementioned problems. The inherent correlation characteristics present in both sensor data and images, as well as the correlation between these two modalities are thoroughly analyzed, to gain a comprehensive understanding of icing characteristics in multimodal data. Specifically, the squeeze-excitation module along with convolutional neural networks are combined to extract the temporal and spatial correlation inherent in sensor data, as well as the spatial and channel correlation inherent in images. Subsequently, the covariance matrix is used to capture the correlation between these two modalities. Moreover, with the assistance of the weight determination structure, this correlation is mapped to the fusion weights. The four-stage training strategy is introduced to guide the network training. The essentiality of the staged training approach and the necessity of correlation extraction in perceiving icing severity are validated in experiments.

This paper investigates one type of distributed constrained optimization problem, e.g., the economic dispatch problem, in the presence of DoS attacks. Therein, multiple DoS attackers are collaborative to impede the communication transmission and change the communication topology at will. Consequently, the convergence and/or optimality of distributed algorithm may be compromised. To reduce the effect of this kind of DoS attacks, a distributed resilient initialization-free Jacobi descent algorithm is proposed. It is designed with three switched control protocols which enable the proposed algorithm reasonably employing the estimations to replace the missing information when attacks occur. Meanwhile, the proposed method is embedded with second order information, resulting in faster convergence speed. Moreover, theoretical analysis results are provided to show that the proposed algorithm can exponentially converge to the global optimal solution of the studied problem. Finally, simulation results tested in IEEE 30-bus system validate its effectiveness and flexibility.Note to Practitioners—The economic dispatch is a key issue in smart grid, which can be formulated as a kind of distributed constrained optimization problem. Since the distributed algorithms work under distributed sensor networks, they are easier to undergo DoS attacks. To address this issue, this paper presents a distributed resilient initialization-free Jacobi descent algorithm, which features strong robustness to resist DoS attacks and faster convergence. Meanwhile, the proposed method is shaped for common constrained optimization problem with better expansibility. We conduct the global convergence and optimality proofs, which benefits the practitioners to estimate the convergence performance, e.g., the convergence rate. Simulations further show the correctness and effectiveness of the proposed method. In future, we will pay more attention on the non-convex constrained optimization problem.

The transition of the power system into a low-carbon power system (LCPS) with a high penetration of renewable energy resources addresses several issues related to energy and climate. However, due to the uncertainty associated with renewable power generation (RPG), deriving an accurate effective locational marginal pricing (LMP) for an LCPS remains a challenge. To address this challenge, we propose a novel information theory-based framework for LMP calculation that quantifies the fluctuations in the LMP due to uncertainty associated with RPG and random loads in an LCPS. First, based on the information entropy levelized cost of energy, we introduce the equivalent cost of RPG to ensure that the cost of RPG is not zero under the LMP mechanism so that it can bid reasonably in the market to provide accurate price signals. We, then, design a security-constrained economic dispatch model incorporating the RPG equivalent cost to balance uncertainty and energy demand in the LCPS electricity market. Furthermore, we propose an uncertainty-constrained model of buses and branches in LCPS based on information theory that is developed to clarify the physical significance of the information that reduces generation and load uncertainty within the LMP framework.

The development of low-carbon power systems has not only elevated the investment costs of power enterprises, but also generated a vast amount of electricity data. The electricity data trading holds promising potential as a primary means to cover investment costs. However, there is a lack of research on the electricity data trading. To address this issue, this article designs an electricity data trading method based on price game and blockchain for low-carbon power systems. It encompasses a data trading framework and the corresponding trading mechanism. The proposed trading framework contains data providers, data consumers, and a blockchain-based information system that plays the role of the data servicer to handle the transactions between data providers and consumers. The proposed trading mechanism mainly consists of three parts: 1) valuation; 2) pricing; and 3) copyrights confirmation. Those parts are executed sequentially to complete the electricity data trading process from valuation to clearing. Specially, the information theory is employed to realize multidimensional electricity data valuation. Further, the data trading game pricing is formulated as a multiobjective optimization problem considering market power constraints to solve. In addition, the digital watermarking combined with blockchain is designed to protect the electricity data copyright. With those components, the designed electricity data trading method enables the power enterprises to make profit from the low-carbon smart energy systems. Finally, experiments demonstrate the effectiveness of the proposed method.

This article proposes a multienergy trading market model based on price matching, aiming to foster multienergy collaboration and enhance energy utilization through individual participation. With the ongoing advancements in energy distribution and marketization, the energy Internet necessitates improved applicability and efficiency for personalized energy responses. To address these requirements, a multienergy trading market model is proposed, which enables the avoidance of user information disclosure and guarantees user trading autonomy. In addition, a joint trading mechanism is designed that accounts for multiple time scales and energy types, consequently reducing trading failures caused by overlooking energy transmission processes. By performing the proposed trading mechanism, the market operator can match various energy types using conversion devices, thereby augmenting matching efficiency. An income mechanism is also established to deter the operator from purposefully evading potential trading opportunities for personal gain. To address the proposed model, an improved hierarchical reinforcement learning algorithm is employed, which effectively overcomes challenges associated with large state action spaces and sparse rewards. Numerical examples are provided to confirm the efficacy of the proposed approach.

This economic dispatch problem has been tended to be solved by using distributed optimization algorithms which are easier to suffer from diversified cyberattacks, e.g., the denial-of-service (DoS) attacks. It leads to enormous secure risks for the economic operation of smart grid. To address this issue, this article aims to propose a distributed secure dispatch method to effectively defend the DoS attacks. First, considering the coexistence of the attack sequence and triggering sequence, the actual affected period and actual safe period are analyzed and defined. It provides an analysis model for the subsequent algorithm design. Then, by designing switched system dynamics along with hybrid-triggering concept, a novel distributed secure dispatch strategy is presented. The proposed method can enable each distributed generator (DG) to reasonably use estimation values and switched rate of system evolution to mitigate the effect of the DoS attacks. Meanwhile, contributed by the designed hybrid-triggering communication strategy, the proposed method takes advantages of reduced communication costs, flexible execution, and fast and reliable communication recuperation among DGs. With those efforts, the proposed method is capable of high robustness to resist the DoS attacks well. Moreover, theoretically analytic results are proposed to verify the correctness of the proposed method. Finally, simulation results are provided to show the feasibility and effectiveness of the proposed method.

The security and economy of multienergy systems (MESs) are directly threatened by the potential cyberattacks. It is of great importance to investigate the effects of cyberattacks, e.g., denial of service (DoS) attacks, on distributed energy management algorithms. To this end, this article focuses on exploring how the frequency and the time of duration of DoS attacks influence the behavior of Newton–Raphson-based distributed energy management (NRBDEM) algorithm for MES and in which condition the optimal operations can still be obtained. First, a switched NRBDEM algorithm is presented, which is composed of the normal operation mode and the attack mode. In the attack mode, the attackers are able to change the communication structure at will and make it unconnected to destroy the convergence of the switched NRBDEM algorithm. Then, by making use of automatons to generate the hybrid time domain, the switched NRBDEM algorithm is further modeled and formulated as a hybrid dynamical system, which provides a mathematical model for the subsequent convergence analysis. Therein, the generated hybrid time domain satisfies the average dwell-time constraint and time-ratio constraint to limit the persistent attacks. Furthermore, we analyze the restrained conditions for persistent attacks, under which the optimality and convergence of the switched NRBDEM algorithm can be guaranteed still. Finally, simulation results demonstrate the effectiveness of the proposed method. Note to Practitioners—The multienergy system (MES) is viewed as a typical cyber-physical system. Since it works in a networked environment, the convergence and optimality of the corresponding distributed energy management algorithms are easily destroyed by various cyberattacks, such as the DoS attack. Few noticeable studies have been documented to investigate the distributed energy management problem for MES under persistent DoS attacks. To address this issue, this article proposes a switched NRBDEM algorithm subject to persistent DoS attacks, which is made up of normal operation mode and attack mode. Moreover, sufficient conditions are derived for the tolerable frequency of attack and the time of duration. It is helpful for the practitioners to know in which conditions the global convergence and optimality can be maintained still. Several simulations are provided to verify the correctness of the proposed theoretical analysis results. Our future work will aim at analyzing the performance of different energy management algorithms under different cyberattacks.

Artificial intelligence (AI) technology has become an important trend to support the analysis and control of complex and time-varying power systems. Although deep reinforcement learning (DRL) has been utilized in the power system field, most of these DRL models are regarded as black boxes, which are difficult to explain and cannot be used on occasions when human operators need to participate. Using the explainable AI (XAI) technology to explain why power system models make certain decisions is as important as the accuracy of the decisions themselves because it ensures trust and transparency in the model decision-making process. The interpretability issue in DRL models in power system emergency control is discussed in this article. The proposed interpretable method is a backpropagation deep explainer based on Shapley additive explanations (SHAPs), which is named the Deep-SHAP method. The Deep-SHAP method is adopted to provide a reasonable interpretable model for a DRL-based emergency control application. For the DRL model, the importance of input features has been quantified to obtain contributions for the outcome of the model. Further, feature classification of the inputs and probabilistic analysis of the outputs in the XAI model is added to interpretability results for better clarity.

In the electric vehicle industry, multilevel inverters (MLIs) are widely used for power conversion in high-power-medium-voltage propulsion drives. The five-level ANPC topology with voltage boosting capability is a promising MLI topology for single-stage solar photovoltaic power conversion. The switching pulses for the MLIs are generated using various PWM techniques. The performance of the five-level boosted ANPC inverter is compared using four distinct unipolar PWM techniques: unipolar sine PWM, unipolar 60◦PWM, unipolar third harmonic injection (THI) PWM, and unipolar zero sequence injection (ZSI) PWM. The performance of these PWM schemes are tested on real-time OPAL-RT platform. Under unipolar THI PWM, the 5L-boosted ANPC outperforms in terms of %THD reduction and higher fundamental output voltage magnitude. Furthermore, the ZSI PWM balances the neutral point potential efficiently.

This article investigates the problem of distributed cooperative energy management of multiple energy bodies with the consideration of both the optimal energy generation/consumption of each participant within single energy body and the optimal energy distribution on the interconnected lines between any pair of energy bodies. First, we define the physical and communication structure of the system formed by many energy bodies, each of which is viewed as a multienergy prosumer. Then, a distributed energy management model is proposed to achieve not only maximum profits of overall energy generation and consumption, but also minimum cost of energy delivery. To address this issue, a distributed double-Newton descent (DDND) algorithm is proposed, which possesses two advantages. On the one hand, by employing second-order information, the concept of Newton descent is embedded into the implementation of the proposed algorithm, resulting in faster convergence speed. On the other hand, the proposed algorithm performs in a fully distributed fashion. As a consequence, each participant can locally obtain its optimal operation as well as the global energy market clearing prices; meanwhile, each energy router can locally obtain the optimal exchanged energy with its neighbor energy routers. Moreover, we prove that the proposed DDND algorithm can asymptotically converge to the global optimal point. As a result, the correctness of the DDND algorithm can be guaranteed in theory. Finally, simulation results validate the effectiveness of the proposed algorithm.

In this paper, a novel adaptive dynamic programming (ADP) algorithm is developed for the infinite-horizon (H∞) optimal control problems with unknown continuous-time (CT) nonlinear systems subject to external disturbances. To facilitate the implementation of the algorithm, generalized fuzzy hyperbolic models (GFHMs) are utilized to establish an identifier-critic architecture, where the identifier is designed to reconstruct the unknown system dynamics, and the GFHM-based critic network is employed to approximate the value functions. The CT H∞optimal control issue is converted into a two-player zero-sum game and the corresponding Hamilton-Jacobi-Isaacs equation is derived. The learning procedure of the critic design is adaptively implemented with the help of the reconstructed model, thus the requirement of the complete system dynamics is relaxed. Furthermore, by the means of Lyapunov direct method, the uniform ultimate boundedness stability analysis of the closed-loop control system is explicitly provided. Finally, to compare the control performances and disturbance attenuation properties of the proposed method and the existing ADP algorithms, two numerical examples are given.

This paper is concerned with the finite-time synchronization problem of coupled hierarchical hybrid delayed neural networks. This coupled hierarchical hybrid neural networks consist of a higher level switching and a lower level Markovian jumping. The time-varying delays are dependent on not only switching signal but also jumping mode. By using a less conservative weighted integral inequality and stochastic multiple Lyapunov-Krasovskii functional, new finite-time synchronization criteria are obtained, which makes the state trajectories be kept within the prescribed bound in a time interval. Finally, an example is proposed to demonstrate the effectiveness of the obtained results.

In this paper, a novel energy management framework for energy Internet with many energy bodies is presented, which features multicoupling of different energy forms, diversified energy roles, and peer-to-peer energy supply/demand, etc. The energy body as an integrated energy unit, which may have various functionalities and play multiple roles at the same time, is formulated for the system model development. Forecasting errors, confidence intervals, and penalty factor are also taken into account to model renewable energy resources to provide tradeoff between optimality and possibility. Furthermore, a novel distributed-consensus alternating direction method of multipliers (ADMM) algorithm, which contains a dynamic average consensus algorithm and distributed ADMM algorithm, is presented to solve the optimal energy management problem of energy Internet. The proposed algorithm can effectively handle the problems of power-heat-gas-coupling, global constraint limits, and nonlinear objective function. With this effort, not only the optimal energy market clearing price but also the optimal energy outputs/demands can be obtained through only local communication and computation. Simulation results are presented to illustrate the effectiveness of the proposed distributed algorithm.

This paper discusses the need for modeling and simulation of electric and hybrid vehicles. Different modeling methods such as physics-based Resistive Companion Form technique and Bond Graph method are presented with powertrain component and system modeling examples. The modeling and simulation capabilities of existing tools such as Powertrain System Analysis Toolkit (PSAT), ADvanced VehIcle SimulatOR (ADVISOR), PSIM, and Virtual Test Bed are demonstrated through application examples. Since power electronics is indispensable in hybrid vehicles, the issue of numerical oscillations in dynamic simulations involving power electronics is briefly addressed.