Changtao Kan

Dr. Changtao Kan


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
25 April 2025 in Algorithms
Verified
Journal Article
Open access
PDF file
Yonglin LiYonglin Li
Yonglin Li
ZLZhao Liu
Zhao Liu
CKChangtao Kan
Changtao Kan
RQRongfei Qiao
Rongfei Qiao
YYYue Yu
Yue Yu
CLChanggang Li
Changgang Li
Amid global decarbonization mandates, urban distribution networks (UDNs) face escalating voltage volatility due to proliferating distributed energy resources (DERs) and emerging loads (e.g., 5G base stations and data centers). While virtual power plants (VPPs) and network reconfiguration mitigate operational risks, extant methods inadequately model load flexibility and suffer from algorithmic stagnation in non-convex optimization. This study proposes a proactive voltage control framework addressing these gaps through three innovations. First, a dynamic cyber-physical load model quantifies 5G/data centers’ demand elasticity as schedulable VPP resources. Second, an Improved Termite Life Cycle Optimizer (ITLCO) integrates chaotic initialization and quantum tunneling to evade local optima, enhancing convergence in high-dimensional spaces. Third, a hierarchical control architecture coordinates the VPP reactive dispatch and topology adaptation via mixed-integer programming. The effectiveness and economic viability of the proposed strategy are validated through multi-scenario simulations of the modified IEEE 33-bus system (represented by 12.66 kV, it is actually oriented to a broader voltage scene). These advancements establish a scalable paradigm for UDNs to harness DERs and next-gen loads while maintaining grid stability under net-zero transitions. The methodology bridges theoretical gaps in flexibility modeling and metaheuristic optimization, offering utilities a computationally efficient tool for real-world implementation.

10 November 2026 in Energies
Verified
Journal Article
Open access
PDF file
QTQi Tao
Qi Tao
HLHuicong Li
Huicong Li
CKChangtao Kan
Changtao Kan
QTQuanwei Tan
Quanwei Tan
LZLai Zhang
Lai Zhang
SZShihui Zhao
Shihui Zhao
The increasing penetration of electric vehicles introduces pronounced randomness, non-stationarity, and multi-scale fluctuations into charging load, making accurate short-term forecasting difficult. Existing methods often suffer from frequency mixing among heterogeneous driving variables, decomposition-induced feature redundancy, and insufficient coordination between local abrupt variation modeling and long-range dependency learning. To address these issues, this paper proposes a multi-scale feature decoupling and local–global synergistic forecasting mechanism. First, an ICEEMDAN-KPCA feature processing strategy is developed to separate stochastic disturbances, periodic fluctuations, and long-term trends in key charging-related variables, and then reorganize the decomposed components in a nonlinear kernel space to suppress redundant information. Second, a serial local–global forecasting architecture is constructed, in which a two-layer LSTM first captures charging-session continuity, short-term state transitions, and local ramping patterns, and the encoded sequence is subsequently modeled by an improved Informer. Different from the standard Informer, relative positional encoding is introduced to strengthen sensitivity to temporal shifts, while dilated causal convolutional distillation enlarges the historical receptive field and preserves abrupt peak-valley and session-boundary variations without future information leakage. Experiments on the Jiaxing EV charging dataset show that the proposed model achieves an RMSE of 56.120 kW, MAE of 42.280 kW, WAPE of 6.990%, and R2 of 0.9627. Compared with nine representative baselines, it achieves the best overall performance, reducing RMSE and MAE by 28.62% and 29.33%, respectively, compared to TimeXer. Ablation results further verify the effectiveness of the proposed model.