Mao Tan

Mao Tan

Auto-generated profile, based on publicly available information

Mao Tan

School of Automation and Electronic Information, Xiangtan University, Xiangtan, China

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
31 December 2019 in IEEE Transactions on Power Systems
Verified
Journal Article
Closed access
MTMao Tan
Mao Tan
SYSiping Yuan
Siping Yuan
SLShuaihu Li
Shuaihu Li
YSYongxin Su
Yongxin Su
HLHui Li
Hui Li
FHFeng He He
Feng He He
Power demand forecasting with high accuracy is a guarantee to keep the balance between power supply and demand. Due to strong volatility of industrial power load, ultra-short-term power demand is difficult to forecast accurately and robustly. To solve this problem, this paper proposes a Long Short-Term Memory (LSTM) network based hybrid ensemble learning forecasting model. A hybrid ensemble strategy---which consists of Bagging, Random Subspace, and Boosting with ensemble pruning---is designed to extract the deep features from multivariate data, and a new loss function that integrates peak demand forecasting error is proposed according to bias-variance tradeoff. Experimental results on open dataset and practical datasets show that the proposed model outperforms several state-of-the-art time series forecasting models, and obtains higher accuracy and robustness to forecast peak demand.

16 March 2023 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
MTMao Tan
Mao Tan
YRYuling Ren
Yuling Ren
RPRui Pan
Rui Pan
LWLing Wang
Ling Wang
JCJie Chen
Jie Chen
The shortage of charging piles and the soaring power demand of charging stations will lead to long waiting times for electric vehicles (EVs) that need to accomplish charging tasks. Most charging scheduling methods pay more attention to the overall waiting time, and they usually do not consider the time-aware fairness among EV users. Moreover, it has become important to schedule EVs effectively to minimize the operating cost of the station. This paper considers the trade-off between the time-aware fairness and overall waiting time of EVs to optimize the individual waiting time. A novel metric, the time-aware fairness index (TAFI), is proposed to evaluate the fairness performance for competing EVs. Therefore, a bi-objective charging and discharging scheduling problem is formulated. A novel online scheduling algorithm based on the dynamic schedulable time of EVs and the energy demand fluctuation of the station is proposed to obtain an optimal scheduling solution. Experimental results indicate that our method effectively reduces the total waiting time while minimizing the maximum individual waiting time and reducing the operating cost of the station. Moveover, the TAFI results confirm that the desired fairness behavior occurs.


18 April 2022 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
MTMao Tan
Mao Tan
CHChenglin Hu
Chenglin Hu
JCJie Chen
Jie Chen
LWLing Wang
Ling Wang
ZLZhengmao Li
Zhengmao Li

25 November 2022 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
MTMao Tan
Mao Tan
ZDZhuocen Dai
Zhuocen Dai
YSYongxin Su
Yongxin Su
CCCaixue Chen
Caixue Chen
LWLing Wang
Ling Wang
JCJie Chen
Jie Chen

1 February 2021 in Information Sciences
Verified
Journal Article
Closed access
RWRui Wang
Rui Wang
WMWubin Ma
Wubin Ma
MTMao Tan
Mao Tan
GWGuohua Wu
Guohua Wu
LWLing Wang
Ling Wang
JXJian Xiong
Jian Xiong