Search

Your search keyword '"Dong, Zhao"' showing total 110 results
Start Over Author "Dong, Zhao" Journal ieee transactions on smart grid
110 results on '"Dong, Zhao"'

4. DAMGAT-Based Interpretable Detection of False Data Injection Attacks in Smart Grids

Author

Su, Xiangjing, Deng, Chao, Yang, Jiajia, Li, Fengyong, Li, Chaojie, Fu, Yang, and Dong, Zhao Yang

Abstract

False data injection attacks (FDIAs) significantly disrupt the secure operation of smart grids by manipulating the measured values collected by intelligent instruments. Existing studies have utilized deep learning techniques to enhance the detection of FDIAs, however, these studies often overlook the spatial correlation between power grid topology and measurement data. Meanwhile, the high complexity of deep neural network severely impedes the interpretability of detection models, resulting in the incredibility of detection results. To address the above challenges, this paper proposes an interpretable deep learning FDIAs detection method, named dual-attention multi-head graph attention network, DAMGAT. The DAMGAT introduces a dual-attention mechanism that incorporates both node feature attention and spatial topology attention into a multi-head graph attention network. This mechanism efficiently aggregates attack characteristics and spatial topology information by dynamically capturing the potential correlations between FDIAs detection and measurement data. Furthermore, the proposed model can provide clear and credible interpretations for high-accuracy detection results via analyzing features and spatial topology attention weights. Extensive simulations are performed using the IEEE 14-bus and 118-bus test systems. The experimental results demonstrate that the proposed model outperforms state-of-the-art FDIA detection methods in terms of accuracy, while also providing reasonable interpretability for features and spatial dimensions.

Published
2024
Full Text
View/download PDF

5. When Mobile Energy Meets Active Distribution Networks: A Security–Economic Coordination Perspective

Author

Zhang, Zhijun, Dong, Zhao Yang, and Yip, Christine

Abstract

This article explores the interaction between active distribution networks (ADN) and mobile energy, specifically mobile charging robots (MCRs) and electric vehicles (EVs). We introduce the concept of MCR operator, who acts as a mediator between EVs and the ADN. To realize the interaction among the three parties, a cloud-edge-terminal control framework is formulated considering the coupling factors with the transportation systems. On this basis, the interaction between MCRs and EVs is achieved based on the game theory, which is implemented in a fully distributed manner to protect the data privacy. To reduce the computation complexity, the game-based interactive problem is further decomposed into a charging price bargaining problem and a charging decision and power regulation problem. Furthermore, the power quality of the ADN is guaranteed through incentivizing the charging/discharging behaviors of MCRs, which is formulated as a coordination between the ADN operator and the MCR operator, and the topology switching is also taken into consideration, thus the voltage regulation ability of the ADN and the economics of the MCR operator can be enhanced at the same time. Simulation results confirm the effectiveness and superiority of the proposed approach, which also indicate that mobile energy and the ADN can achieve a win-win situation by benefiting all parties: Improving the utility for the EV aggregator by 35.48% (reducing the charging cost for EV owners), increasing the charging revenue for the MCR operator by 12%, and addressing the voltage issue for the ADN with a 100% voltage security rate.

Published
2024
Full Text
View/download PDF

6. Adaptive Horizontal Federated Learning-Based Demand Response Baseline Load Estimation

Author

Wang, Renjun, Qiu, Haifeng, Gao, Hongjun, Li, Chaojie, Dong, Zhao Yang, and Liu, Junyong

Abstract

To improve the operational security and reliability of distribution networks, distribution network operators will encourage customers to modify their demand profiles and then give them financial compensation. The compensation is always settled based on customer baseline load (CBL). The estimation of CBL can be achieved using both traditional historical data methods and non-participant data methods. However, relying solely on a single method for estimating baseline load for some residential customers may result in significant estimation errors. To estimate baselines for residential loads under different conditions, this paper proposes a novel deep learning method that intelligently selects historical data-based CBL and non-participant data-based CBL. This method provides a special way for taking advantage of the historical load data of demand response (DR) participant and the concurrent load data of nonparticipants. Moreover, to preserve the privacy of residential customers, a horizontal federated learning framework is proposed to train local neural networks in residential units. In the federated learning framework, a novel adaptive learning rate method is proposed to improve the performance of local neural networks under low global aggregation frequency. Compared with the state-of-the-art CBL estimation methods, the improved federated learning method can significantly reduce the seriously inaccurate estimation and improve the overall performance of CBL estimation under various condition. The effectiveness and superiority of the proposed method have been verified on a real-world load dataset.

Published
2024
Full Text
View/download PDF

20. Unlock the Thermal Flexibility in Integrated Energy Systems: A Robust Nodal Pricing Approach for Thermal Loads

Author

Lu, Shuai, Gu, Wei, Xu, Yijun, Dong, Zhao Yang, Sun, Lingling, Zhang, Hao, and Ding, Shixing

Abstract

The thermal flexibility of buildings in integrated energy systems (IES) has great potential to improve the operational economy and wind power consumption. To incentivize the thermal flexibility of buildings under uncertainties, we propose a robust nodal pricing (RNP) model for thermal loads based on the Stackelberg game approach. The RNP model adopts a bilevel framework in which the IES operator plays the leader at the upper level while the thermal load aggregators (TLA) play the followers at the lower level. The IES operator problem optimizes the heat prices and dispatch plan, which is modeled as a two-stage robust optimization problem to address the uncertainties in the renewables and the loads. The TLA problem optimizes the thermal loads of buildings to minimize the energy cost and thermal comfort loss, which is modeled as a distributionally robust chance-constrained optimization problem to address the uncertainty in outdoor temperature. Then, we convert the TLA model into deterministic quadratic programming and prove that Slater’s condition holds under a mild assumption. Using it, the TLA model is equivalently converted into Karush-Kuhn-Tucker conditions, leading to a reformulation of a classical two-stage robust optimization model for the RNP model. Case studies compare different pricing methods and verify the superiority of the proposed method.

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results