This article presents a decentralized dynamic event-sampled control (ESC) strategy for multi-unit power systems (MUPSs) subject to mismatched interconnections. Initially, with the introduction of a dynamic event-sampling mechanism, the decentralized ESC problem of MUPSs is converted into a set of event-sampled optimal control problems of auxiliary subsystems. It is demonstrated that all the solutions of the event-sampled Hamilton-Jacobi-Bellman equations (ES-HJBEs) arising in these optimal control problems together constitute the decentralized dynamic ESC law. Then, in order to solve the ES-HJBEs, the critic neural networks (CNNs) within the adaptive dynamic programming framework are constructed. The CNNs’ weights are updated via simultaneously using the gradient descent method and concurrent learning. The benefits of such a tuning rule are that it not only makes full use of state data (including historical and instantaneous state data) but also no longer requires the persistence of excitation condition. Moreover, uniform ultimate boundedness of the closed-loop auxiliary subsystem states and the CNNs’ weight estimation errors are proved via Lyapunov approach. Finally, simulations of a three-unit power system are given to validate the present decentralized dynamic ESC scheme.

In actual ac microgrids (MGs), the design of distributed secondary control methods requires information exchanges between distributed generators (DGs) by a communication network. This means MGs are potentially suffering from model-free Denial of Service (DoS) attacks and are affected by the constraints of transmission rate simultaneously. Accordingly, we develop a novel distributed security control strategy based on quantization to ensure the stable and economic operation of ac MGs. Considering DoS attacks can exacerbate the rate constraints inherent in communication networks, a quantization controller with a minimal quantization level is designed to account for extreme scenarios. This ensures that ac MGs achieves their control objectives by transmitting only 1 bit of data at each successful transmission instance while guaranteeing that the quantized signal does not exceed the range of quantizer throughout the entire process. In addition, the developed control strategy can synchronize the output voltage and frequency of DGs to their reference values, respectively, and achieve active power-sharing. Besides, the quantization level can be dynamically adjusted according to the actual situation of ac MGs to improve the operation effect of the algorithm. Finally, the performance of the proposed distributed security control strategy and comparisons with other research are evaluated on an ac MG composed of seven DGs in real-time testing equipment built on RT-LAB.

Recent advances in neural networks have significantly improved electricity theft detection, achieving higher detection accuracy compared to earlier methods (e.g., support vector machine and decision tree). However, the performance of these networks is still restricted by the class imbalance issue, which causes the neural networks to bias toward classifying unknown users as the majority class (i.e., normal users). While previous works have developed oversampling and data augmentation techniques to alleviate this problem at the data level, these techniques usually replicate existing fraudulent samples or generate similar ones, which can lead to overfitting and, thus, limit model performance. To this end, this article aims to mitigate the class imbalance issue from a novel perspective at the algorithmic level. Specifically, a sample-weighted (SW) loss is proposed to efficiently train neural networks by assigning different weights to samples based on their importance, in contrast to most existing works, which treat all samples equally. Notably, the proposed SW loss is independent of any specific model architecture, meaning that it can be seamlessly integrated with various neural networks to update their weights for electricity theft detection. Simulation results on real-world datasets show that the proposed SW loss outperforms baselines (e.g., binary cross entropy loss, class-balanced loss, oversampling, and data augmentation), with an increase of about 0.27% to 9.78% in mean average precision and 0.14% to 2.92% in the area under the curve, respectively.

High penetration in distributed photovoltaics (PVs) enhances the resilience of distribution network operations. However, it brings many uncertain issues such as the voltage and harmonic fluctuations that may affect the distribution network stability. Therefore, the determination of the PV location and capacity is of vital importance for smart distribution network planning. Considering the fluctuation of PV outputs and the robustness of optimization results, this paper proposes an adjustable robust optimization method for large-scale PV planning in smart distribution networks. The AC power flow is first converted into a convex program by the linearization theory, and the bi-level optimization is converted to a single-layer optimization problem using the strong duality theory. A hybrid algorithm based on the integration of grey wolf optimization (GWO) and improved particle swarm optimization (IPSO), named GWO-IPSO, is proposed to determine the robust optimal location and the capacity of distributed PVs. The proposed method is verified based on the IEEE 69–bus radial distribution network case study. The proposed method efficiently adapts to parameter uncertainties resulting from extreme scenarios and delivers better performance than general heuristic methods.

Few-shot learning (FSL) aims to learn a model that can identify unseen classes using only a few training samples from each class. Most of the existing FSL methods adopt a manually predefined metric function to measure the relationship between a sample and a class, which usually require tremendous efforts and domain knowledge. In contrast, we propose a novel model called automatic metric search (Auto-MS), in which an Auto-MS space is designed for automatically searching task-specific metric functions. This allows us to further develop a new searching strategy to facilitate automated FSL. More specifically, by incorporating the episode-training mechanism into the bilevel search strategy, the proposed search strategy can effectively optimize the network weights and structural parameters of the few-shot model. Extensive experiments on the miniImageNet and tieredImageNet datasets demonstrate that the proposed Auto-MS achieves superior performance in FSL problems.

Accurate acquisition of real-time electromechanical dynamic states of synchronous generators plays an essential role in power systems. The phasor measurement units (PMUs) are widely used in data acquisition of synchronous generator operation parameters, which can capture the dynamic responses of generators. However, distortion of measurement results of synchronous generator operation parameters is inevitable due to various reasons, such as device failure and operating environment interference and so on. Meanwhile, it is hard to transmit gigantic volumes of data to the information center due to limited communication bandwidth. To tackle these challenges, this article proposes a dynamic state estimation method for synchronous generators with event-triggered scheme. The proposed method first establishes a non-linear model to describe the dynamics of generators. Then, a measure-based event-triggering scheme is adopted to schedule the data transmission from the sensor to estimator, thus reducing communication pressure and enhanced resource utilization. Finally, an improved regularized particle filter (IRPF) algorithm is designed to guarantee the estimation performance. To this end, the genetic algorithm is used to optimize the particles sampled by regularized particle filter algorithm, which can solve particle exhaustion problem. The CEPRI7 system is used to verify the performance of the proposed method.

Highway charging scheduling for battery electric vehicles is a complex research issue depending on the fast charging capacity provided and the information available in coordinating drivers’ multiple charges at charging stations. Moreover, user’s partially-known preferences and potential dynamic events remain extra challenges in maximizing user’s satisfaction, improving the revenue of highway charging stations and utilizing the limited charging capacities. In such separate and simultaneous markets, users are reasonably modelled as the self-interested agents who aim to advance their own benefits but negotiable on their charging schedules. In this paper, we propose a simultaneous multi-round auction to address the highway charging scheduling problem, where users are allowed to bid and compromise on their preferred stops, charging time and energy simultaneously at separate charging stations. The objective is to maximize the total revenue of these stations. In the course of auction, users can gradually figure out how can their charges fit together by adaptively adjusting their bids placed at different stations. As a result, high-quality solutions are obtained and user’s privacy can be preserved by progressively eliciting their private preferences as necessary. In addition, we also develop a dynamic scheduling algorithm to address the changes of user’s reserved charges and unexpected arrivals of other vehicles. We conduct extensive experiments to validate our approach, the results demonstrate that it can achieve high efficiency with partial private information, as well as a higher revenue with dynamic scheduling algorithm. It can also greatly reduce the total waiting time of users against the first-come-first-serve policy.

Photovoltaics intelligent edge terminals (PV IETs) are new devices for data acquisition and management of PV power station. However, due to the massive, scattered, and disordered nature of PV stations and the expensive price of PV IET, installing a PV IET at each PV station has prohibited for large-scale adoption. Therefore, to reduce the life cycle cost of PV IET in a region, this paper proposes an optimal configuration method for PV IET. We propose a mathematical model for the optimal configuration of PV IETs. For a given regional grid, the model aims to obtain the optimal number and location of PV IETs and the connection mode between PV IETs and PV power stations. In addition, an improved Harris hawk optimization (IHHO) is proposed to solve the nonlinear mathematical model. A case study is carried out under different problem sizes, boundary and devices parameters. The simulation results show that under different case, the PV IET configuration method in this paper can obtain lower life cycle cost than the conventional method, and IHHO has higher accuracy than other algorithms. The optimal configuration method in this article can effectively solve the problem of the optimal configuration of PV IET.