Changchun Cai

Changchun Cai


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
30 June 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
CCChangchun Cai
Changchun Cai
YLYuanjia Li
Yuanjia Li
ZSZhenghua Su
Zhenghua Su
TZTianqi Zhu
Tianqi Zhu
YHYaoyao He
Yaoyao He
With the continuous increase in user-side flexible controllable resources connected into a distribution system, the components of electrical load become too diverse and difficult to be accuracy forecasted. A short-term load forecast method that integrates variational modal decomposition (VMD), gated recurrent unit (GRU) and time convolutional network (TCN) into a hybrid network is proposed in this paper. Firstly, original electrical load sequence data with noise are decomposed into intrinsic IMF components with different frequencies and amplitudes based on the VMD method. Secondly, a combined load forecasting method based on the GRU and TCN network is proposed for the high and low-frequency load subsequent signals, respectively. Finally, the high and low-frequency signals forecasting results of the GRU and TCN network are rebuilt for the final load forecasting. The experiment results based on actual operation data (data set 1) and simulation data (data set 2), which show that the proposed method can reduce the forecasting error by 36.20% and 10.8%, respectively, in comparison with VMD-GRU. The reliability and accuracy of the proposed method is verified through the comparison with other methods such as LSTM, Prophet and XG Boost.

1 September 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
CCChangchun Cai
Changchun Cai
YTYuan Tao
Yuan Tao
TZTianqi Zhu
Tianqi Zhu
ZDZhixiang Deng
Zhixiang Deng
Accurate load forecasting guarantees the stable and economic operation of power systems. With the increasing integration of distributed generations and electrical vehicles, the variability and randomness characteristics of individual loads and the distributed generation has increased the complexity of power loads in power systems. Hence, accurate and robust load forecasting results are becoming increasingly important in modern power systems. The paper presents a multi-layer stacked bidirectional long short-term memory (LSTM)-based short-term load forecasting framework; the method includes neural network architecture, model training, and bootstrapping. In the proposed method, reverse computing is combined with forward computing, and a feedback calculation mechanism is designed to solve the coupling of before and after time-series information of the power load. In order to improve the convergence of the algorithm, deep learning training is introduced to mine the correlation between historical loads, and the multi-layer stacked style of the network is established to manage the power load information. Finally, actual data are applied to test the proposed method, and a comparison of the results of the proposed method with different methods shows that the proposed method can extract dynamic features from the data as well as make accurate predictions, and the availability of the proposed method is verified with real operational data.

17 February 2023 in The Visual Computer
Verified
Journal Article
Closed access
PDF file
XLXinbiao Lu
Xinbiao Lu
XXXupeng Xie
Xupeng Xie
CYChunlin Ye
Chunlin Ye
HXHao Xing
Hao Xing
ZLZecheng Liu
Zecheng Liu
CCChangchun Cai
Changchun Cai

26 April 2023 in Electronics
Verified
Journal Article
Open access
PDF file
ZQZhouyi Qian
Zhouyi Qian
ZDZhixiang Deng
Zhixiang Deng
CCChangchun Cai
Changchun Cai
HLHaochen Li
Haochen Li
Unmanned aerial vehicles (UAV) can serve as aerial base stations for users due to their flexibility, low cost, and other characteristics. However, due to the high flight position of UAVs, the air-to-ground (ATG) channels usually dominate with line-of-sight (LoS), which can be easily eavesdropped by multiple eavesdroppers. This poses a challenge to secure communication between UAVs and ground users. In this paper, we study a UAV-aided secure communication in an urban scenario where a legitimate UAV Alice transmits confidential information to a legitimate user Bob on the ground in the presence of several eavesdroppers around it and a UAV Jammer sends artificial noise to interfere with the eavesdroppers. We aim to maximize the physical layer secrecy rates in the system by jointly optimizing the trajectories of UAVs and their transmitting power. Considering the time-varying characteristics of channels, this problem is modeled as a Markov decision process (MDP). An improved algorithm based on double-DQN is proposed in the paper to solve this MDP problem. Simulation results show that the proposed algorithm can converge quickly under different environments, and the UAV transmitter and UAV jammers can find the optimal location correctly to maximize the information secrecy rate. It also shows that the double-DQN (DDQN) based algorithm works better than the Q-learning and deep Q-learning network (DQN).

13 October 2023 in Frontiers in Energy Research
Verified
Journal Article
Open access
CCChangchun Cai
Changchun Cai
YLYuanjia Li
Yuanjia Li
YHYaoyao He
Yaoyao He
LGLei Guo
Lei Guo
In order to achieve the economic consumption of renewable energy in a multi-energy power system including wind/PV/hydropower and energy storage, a two-tier coordinated optimal scheduling method based on generative adversarial network (GAN) scenario generation is proposed in this paper. First, an upper-tier optimization model for the operation of the load and storage system is established to achieve the objective of minimizing the load fluctuation and the cost of energy storage plants. Furthermore, a lower-tier optimization model to minimize the system operation cost and tide risk is established for the optimization operation of renewable energy generation. Second, an improved generative adversarial network is proposed to generate the operation scenes for evaluating the uncertainty characteristics of the wind and photovoltaic (PV) generation. Then, an improved coati optimization algorithm (COA) is used to solve the proposed optimization problem. Finally, the IEEE 30-bus system is selected as the example system for verifying the proposed method. The simulation results corroborate the validity and feasibility of the proposed method.

30 April 2026 in Mathematics
Verified
Journal Article
Open access
PDF file
YLYining Lin
Yining Lin
CCChangchun Cai
Changchun Cai
Reliable anomaly early warning for hydropower station sump wells remains challenging due to the strong nonlinearity of water level dynamics and the limited adaptability of conventional fixed-threshold alarms. Here, we present a hybrid deep learning framework—termed CNN–Attention–LSTM–BO—that fuses multi-scale local feature extraction, adaptive temporal weighting, and sequential dependency modeling within a unified architecture, with all critical hyperparameters tuned via Bayesian optimization. A four-dimensional input representation is first constructed from the raw water level signal and its first- and second-order differences together with the drainage pump operating state, capturing both trend and transient information. One-dimensional convolutions at multiple kernel scales encode short-range fluctuation patterns, a Bahdanau-style temporal attention layer selectively amplifies informative time steps, and a stacked LSTM propagates long-horizon risk dependencies. At the decision stage, a dual dynamic thresholding scheme couples an improved 3σ criterion with kernel density estimation (KDE) to partition the smoothed risk score into three graded alert levels (normal/warning/critical), replacing the binary alarm paradigm. Experiments on the SWaT benchmark yield an average area under the ROC curve (AUC) of 0.9246, an average Accuracy of 0.8812, and a best single-well false alarm rate (FAR) of 3.21% (Well-4), with an average FAR of 8.97% across three wells, outperforming both traditional limit-value alarms and ablated variants lacking CNN or attention modules.