Zhongliang Lyu

Dr. Zhongliang Lyu

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 April 2020 in IEEE Systems Journal
Verified
Journal Article
Closed access
ZLZhongliang Lyu
Zhongliang Lyu
HWHua Wei
Hua Wei
XBXiaoqing Bai
Xiaoqing Bai
CLChunjie Lian
Chunjie Lian
This article proposes a microservice-based architecture for an energy management system (MS-EMS) to address the fragility, poor flexibility, and hardware dependence of EMSs. Compared with the service-oriented architecture (SOA), the proposed architecture can significantly improve the load performance and scalability of an EMS through fine-grained decomposition of the system and decentralized data management. Container and cluster technologies are used to manage the microservices. A $k$ -fault $(k\geq 2)$ -tolerant model is proposed to improve the reliability of the MS-EMS. The model employs containerized microservices as essential components to achieve a parallel connection of the essential components using the horizontal-scale technology of the containers. On the other hand, a MILP model-based algorithm for managing computing resources is also suggested. By minimizing the number of worker nodes of the cluster, where the MS-EMS is deployed, we can improve the utilization of the computing resources and avoid unnecessary costs. The result of the performance analysis showed that the reliability of the MS-EMS is $99.99965625\text{\%}$ , which is two orders and one order of magnitude higher than those of the existing EMSs and the SOA-based EMS (S-EMS), respectively. Moreover, the cost of the MS-EMS is also lower than those of the existing EMSs and S-EMSs. The proposed architecture is implemented in a real-power system and has shown favorable operation performances, indicating a promising prospect for future applications.

17 May 2021 in IEEE Access
Verified
Journal Article
Open access
ZLZongsheng Li
Zongsheng Li
HWHua Wei
Hua Wei
ZLZhongliang Lyu
Zhongliang Lyu
CLChunjie Lian
Chunjie Lian
This paper proposes an energy management system (EMS) architecture based on the Kubernetes container cluster to solve the problem of traditional EMSs being unable to simultaneously achieve high reliability and high resource utilization. Container cluster technology is used to encapsulate, isolate and deploy applications, which solves the problem of low system reliability caused by interlocking failures. Discrete Markov theory is applied to propose a dynamic Pod fault-tolerant EMS model. The results of the solution model are used to adjust the Pod redundancy in real-time to achieve the highest reliability to satisfy physical resource constraints. The results of the performance analysis show that the reliability of the proposed architecture is 99.9999504%. Compared with the EMS of the service-oriented architecture (SOA), the annual failure time is reduced from 3.83 minutes to 0.26 minutes. The comprehensive utilization of hardware resources increases by approximately 20%, and performance indicators such as the peak access success rate improve significantly. The proposed architecture is implemented in a real-power system, with good operating results and broad application prospects.

22 November 2021 in IEEE Access
Verified
Journal Article
Open access
HWHongbo Wei
Hongbo Wei
HWHua Wei
Hua Wei
ZLZhongliang Lyu
Zhongliang Lyu
XBXiaoqing Bai
Xiaoqing Bai
JTJunyang Tian
Junyang Tian
This paper proposes a faulty feeder detection method based on Deep Belief Network (DBN) of deep learning theory for the neutral non-effectively grounded systems. It consists of two steps: firstly, a DBN-based faulty feeder detection model is built with feeder current, power and power factor as input feature parameters. Then, the input feature data are obtained during the single-phase ground fault from the master station of power dispatching system, which will construct a training set. By unsupervised pre-training and supervised fine-tuning, the proposed model obtains the mapping relationship between raw data and fault characteristics and realizes the faulty feeder detection. The advantage of the proposed method is using millisecond-level data in power dispatching system directly. Moreover, the sampling device does not need to install, which significantly reduces the construction costs and is of strong adaptability. The analyzed result using the ground fault data of an actual substation for more than two years shows that the proposed method has a better performance than SVM and BP neural network, and the accuracy is up to 94.7%. The proposed method has been implemented in Lipu Power Grid, Guangxi, China with excellent application effect and extensive application prospects.

1 January 2024 in International Transactions on Electrical Energy Systems
Verified
Journal Article
Open access
BYBo Yang
Bo Yang
ZLZhongliang Lyu
Zhongliang Lyu
HWHua Wei
Hua Wei
Data anomaly detection in small hydropower stations is an important research area because it positively affects the reliability of optimal scheduling and subsequent analytical studies of small hydropower station clusters. Although many anomaly detection algorithms have been introduced in the data preprocessing stage in various research areas, there is still little research on effective and highly reliable anomaly detection systems for practical applications in small hydropower stations. Therefore, this paper proposes a real‐time data anomaly detection system for small hydropower clusters (RDADS‐SHC) considering multiple time series. It addresses the difficulties of timely detection, alerting, and management of real‐time data anomalies (errors, omissions, and so on) in existing small hydropower stations. It proposes a real‐time data anomaly detection algorithm for small hydropower stations integrated with the Z‐score and dynamic time warping, which can detect and process abnormal information more accurately and efficiently, thereby improving the stability and reliability of data sampling. The paper proposes a Keepalived‐based hot‐standby RDADS‐SHC deployment model with m (m ≥ 2) units. It can automatically remove and restart faulty services and switch to their standbys, which significantly improve the reliability of the proposed system, ensuring the safe and stable operation of related functional services. This paper can detect anomalous data more accurately, and the system is more stable and reliable in a cluster detection environment. The actual operation has shown that compared with existing anomaly detection systems, the architecture and algorithms proposed in this paper can detect anomalous data more accurately, and the system is more stable and reliable in the small hydropower cluster detection environment. It solves abnormal data management in small hydropower stations and provides reliable support for subsequent analysis and decision‐making.

1 September 2019
Verified
Conference Paper
Closed access
LZLe Zhang
Le Zhang
HWHua Wei
Hua Wei
ZLZhongliang Lyu
Zhongliang Lyu
HHHong Hu
Hong Hu
This paper presents a small hydro group WebGIS based on HTML5, which solves the problems of large number, wide distribution, disorderly management and difficult maintenance of small hydro group. The tile pyramid technology is used to migrate the map data needed by the small hydro group GIS to the local area for processing, storage and display, which realizes the localization of maps. Using HTML5 Canvas, the browser uses JavaScript to render graphics and draw dynamic graphics, which enriches the user’s experience. Data information such as water level, installed capacity and output load of small hydro station is transmitted between server and client through HTML5 WebSocket and WebStorage. The real-time data exchange between server and map interface is realized by using these technologies. The Small Hydro Group GIS adopts the service-oriented architecture (SOA) based on Web services, which enhances the compatibility, integration and interoperability of the system. The actual operation of a dispatching center shows that the system solves the problem of data management of hydro stations in the past, and can display the geographic information and operation status of hydro stations in real time and accurately. This system provides an integrated management platform for dispatchers.

2 November 2022 in Journal of Electrical Engineering & Technology
Verified
Journal Article
Closed access
PDF file
XSXianxin Su
Xianxin Su
HWHua Wei
Hua Wei
HWHongbo Wei
Hongbo Wei
ZLZhongliang Lyu
Zhongliang Lyu
XZXuan Zhang
Xuan Zhang
WGWei Gao
Wei Gao