Lin Liu

Lin Liu

Auto-generated profile, based on publicly available information

Lin Liu

Power Dispatching & Control Center of China Southern Power Grid, Guangzhou 510525, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
28 December 2024 in Processes
Verified
Journal Article
Open access
PDF file
JYJingwei Yang
Jingwei Yang
YCYitong Chen
Yitong Chen
QHQiang Huang
Qiang Huang
GWGuilong Wu
Guilong Wu
LLLin Liu
Lin Liu
YHYu Huang
Yu Huang
As a key technology for future decarbonization, storage batteries are widely used in areas such as electric vehicles and power systems. However, battery aging inevitably limits their broader application. To address the low accuracy in predicting discharge voltage under different aging states, this paper proposes the IWOA-ATCN method based on a TCN model with a sliding window mechanism. First, the improved whale optimization algorithm (IWOA) is employed to optimize the hyperparameters in the TCN model, including window size and sliding step, to obtain the optimal sample structure. Then, the temporal attention mechanism is introduced into the TCN model to accurately capture the temporal correlation of discharge voltage, thereby improving the prediction accuracy of long time series data. Finally, the model is tested on the NASA dataset with an RMSE of 0.0072, MAE of 0.0046, and R2 of 0.9984. The test results on the PL Sample dataset showed RMSE of 0.0081, MAE of 0.0040, and R2 of 0.9983. It is indicated that the prediction accuracy and stability of the IWOA-ATCN model are higher than other models, such as BP, RNN, and LSTM.

26 August 2024 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
XWXin Wu
Xin Wu
YYYawen Yu
Yawen Yu
YLYi Liu
Yi Liu
LLLin Liu
Lin Liu
XLXiang Li
Xiang Li
The hierarchical aggregation and control of electric vehicles (EVs) is an effective way to promote the consumption of clean energy and ensure the balance of power demand-supply. In the case of increasingly insufficient wireless resources of cellular networks, one challenging problem is how to guarantee the realtime and accurate service interaction requirements of massive services in EV aggregation response. In this paper, in order to support the communication process of EV hierarchical aggregation and control, a hierarchical communication network architecture of “Central cloud- Regional cloud- Edge unit- EVs” is proposed. Considering the differences of service processing functions and communication demands of each layer, the utility function models are constructed to describe the different demands on the timeliness and accuracy. And based on the utility functions, a network communication resource allocation model is established to allocate power and channel resources on demand. Finally, to reduce the amount of computation, this paper proposes the joint allocation algorithm of power and channel resources based on the improved water-filling algorithm, adaptive particle swarm optimization algorithm and two-sided matching theory. The simulation experiment results illustrate that the total utility of the proposed algorithm is increased by 0.43 times on average compared with the channel average allocation (H-A), and 0.08 times compared with the layer-bylayer optimization (H-NJO)

30 September 2024 in Photonics
Verified
Journal Article
Open access
PDF file
WLWeihua Lian
Weihua Lian
XSXingrui Su
Xingrui Su
WLWei Li
Wei Li
BWBin Wu
Bin Wu
XFXiaofang Feng
Xiaofang Feng
KHKaijing Hu
Kaijing Hu
Lightning strike is one of the main factors affecting power transmission lines and may lead to broken strands and damage of transmission lines, resulting in abnormal power supply. To improve the accuracy of lightning location, this paper presents a polarization optical time-domain reflectometer (POTDR) lightning location method based on orthogonal coding technology. The lightning strike point can be located by detecting the state of polarization (SOP) mutation of Rayleigh backscattering in the POTDR system. The orthogonal coding technology is used to improve the distance and accuracy of POTDR lightning location. Through calculation and simulation analysis, the location accuracy is significantly improved at the same sensing distance compared with the ordinary POTDR lightning location method. The lightning strike location error can be limited to 200 m in 20 km sensing distance which meets the actual engineering needs. The results of this paper are important to improve the operation and maintenance efficiency of transmission lines and reduce maintenance costs in the power industry.