Kuangpu Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kuangpu Liu has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
Bin Zhang
AAU Energy, Aalborg University, Aalborg, Denmark
2 shared publications- Wenlong Liao
School of Engineering, University of Leicester, Leicester, U.K.
2 shared publications - Zhe Yang
Department of Electrical and Electronic Engineering, Imperial College London, London, U.K.
2 shared publications - Bin Feng
College of Electrical Engineering, Zhejiang University, Hangzhou, China
1 shared publication Cheng Luo
Department of Technology Development, TBEA Xian Electric Technology Company Ltd., Xian, China
1 shared publication- Ruijin Zhu
School of Electrical Engineering Tibet Agriculture and Animal Husbandry University Linzhi China
1 shared publication
Latest Publications
- 29 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 16 (2) , 1422-1433
Near-Optimal Energy Management Strategy for a Grid-Forming PV and Hybrid Energy Storage System
Integration of Li-ion batteries and supercapacitors (SCs) into PV plants enables a hybrid PV system with more grid functions like power filtering and frequency regulation. Above that, an energy management system (EMS) plays a key role in achieving grid functions and economic performance. However, previous efforts focused on advanced forecast methods without considering real-time EMS. This paper thus aims to develop a practical real-time EMS with near-optimal performance for the degradation of the hybrid energy storage system (HESS). Firstly, a variational mode decomposition (VMD) method is combined with a long short-term memory (LSTM) network to decompose and learn feature parameters of typical historical weather data, improving forecast accuracy and shifting the operation mode periodically. Then, the mixed integer linear programming approach is utilized to find out the optimal control mode in different operation scenarios, and three-segment rules are extracted from the optimization results. Finally, the deep learning-based real-time EMS is developed. Numeric simulations validate that the proposed EMS can achieve near-optimal performance with a low computation burden. Besides, the proposed strategy can reduce the degradation cost by up to 80% compared with competitive rule-based strategies.
- 29 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 16 (2) , 1422-1433
Near-Optimal Energy Management Strategy for a Grid-Forming PV and Hybrid Energy Storage System
Integration of Li-ion batteries and supercapacitors (SCs) into PV plants enables a hybrid PV system with more grid functions like power filtering and frequency regulation. Above that, an energy management system (EMS) plays a key role in achieving grid functions and economic performance. However, previous efforts focused on advanced forecast methods without considering real-time EMS. This paper thus aims to develop a practical real-time EMS with near-optimal performance for the degradation of the hybrid energy storage system (HESS). Firstly, a variational mode decomposition (VMD) method is combined with a long short-term memory (LSTM) network to decompose and learn feature parameters of typical historical weather data, improving forecast accuracy and shifting the operation mode periodically. Then, the mixed integer linear programming approach is utilized to find out the optimal control mode in different operation scenarios, and three-segment rules are extracted from the optimization results. Finally, the deep learning-based real-time EMS is developed. Numeric simulations validate that the proposed EMS can achieve near-optimal performance with a low computation burden. Besides, the proposed strategy can reduce the degradation cost by up to 80% compared with competitive rule-based strategies.
- 20 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (4) , 5074-5086
Electricity Theft Detection Using Dynamic Graph Construction and Graph Attention Network
The integrations of advanced metering infrastructure and smart meters make it possible to detect electricity thieves by analyzing electricity consumption readings. However, the detection accuracies of traditional models are limited due to their difficulty in capturing the periodicity and latent features from electricity consumption readings. To solve this problem, a graph attention network (GAT)-based model is proposed to improve the detection accuracy from a fresh viewpoint on graph domains. First, a new strategy is presented to transform raw one-dimensional electricity consumption readings into dynamic graphs, which represent the features and periodicity through feature matrices and correlation matrices, respectively. Then, a GAT is migrated from traditional graph inferences into electricity theft detection, in which necessary adjustments are made on structures to capture periodicity and latent features from dynamic graphs. Case studies show that the proposed model outperforms popular baselines for a wide range of training ratios and fraudulent ratios.
- 20 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (4) , 5074-5086
Electricity Theft Detection Using Dynamic Graph Construction and Graph Attention Network
The integrations of advanced metering infrastructure and smart meters make it possible to detect electricity thieves by analyzing electricity consumption readings. However, the detection accuracies of traditional models are limited due to their difficulty in capturing the periodicity and latent features from electricity consumption readings. To solve this problem, a graph attention network (GAT)-based model is proposed to improve the detection accuracy from a fresh viewpoint on graph domains. First, a new strategy is presented to transform raw one-dimensional electricity consumption readings into dynamic graphs, which represent the features and periodicity through feature matrices and correlation matrices, respectively. Then, a GAT is migrated from traditional graph inferences into electricity theft detection, in which necessary adjustments are made on structures to capture periodicity and latent features from dynamic graphs. Case studies show that the proposed model outperforms popular baselines for a wide range of training ratios and fraudulent ratios.
- 8 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. PP (08858950) , 1-13
Electricity Theft Detection Using Euclidean and Graph Convolutional Neural Networks
The widespread penetration of advanced metering infrastructure brings an opportunity to detect electricity theft by analyzing the electricity consumption data collected from smart meters. However, existing models have poor performance in electricity theft detection, since most of them fail to capture the time dependence, periodicity, and latent feature from complex electricity consumption data. To address above concerns, a graph convolutional neural network (GCN) and a Euclidean convolutional neural network (CNN) are combined to form a novel model for electricity theft detection in this paper. On one hand, the high-dimensional power load curves are modeled as a graph from a new perspective on graph theory. Then, the GCN depicts the time dependence and periodicity by performing graph convolutional operations. On the other hand, the CNN captures the latent features from the power load curves by carrying out Euclidean convolutional procedures. Numerical simulations show that the proposed model integrates the benefits of GCN and CNN, leading to superiority over the popular benchmarks in electricity theft detection.
- 8 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. PP (08858950) , 1-13
Electricity Theft Detection Using Euclidean and Graph Convolutional Neural Networks
The widespread penetration of advanced metering infrastructure brings an opportunity to detect electricity theft by analyzing the electricity consumption data collected from smart meters. However, existing models have poor performance in electricity theft detection, since most of them fail to capture the time dependence, periodicity, and latent feature from complex electricity consumption data. To address above concerns, a graph convolutional neural network (GCN) and a Euclidean convolutional neural network (CNN) are combined to form a novel model for electricity theft detection in this paper. On one hand, the high-dimensional power load curves are modeled as a graph from a new perspective on graph theory. Then, the GCN depicts the time dependence and periodicity by performing graph convolutional operations. On the other hand, the CNN captures the latent features from the power load curves by carrying out Euclidean convolutional procedures. Numerical simulations show that the proposed model integrates the benefits of GCN and CNN, leading to superiority over the popular benchmarks in electricity theft detection.