Hao Mai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hao Mai has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Qingfang Teng
School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730050, China
2 shared publications - Jing Chen
School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730050, China
1 shared publication - Lili Qu
School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China
1 shared publication - Xiaojian Wang
School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730050, China
1 shared publication
Latest Publications
- Open Access
Optimal Control Method for Microgrid Distributed Generation Based on Multi-Agent Adaptive Decision-Making
In addressing the challenges of strong power generation fluctuation, complex load variation, and dynamic topology changes in microgrid operation, this paper puts forward a proposal for optimal control methodology for distributed generation based on multi-agent adaptive decision-making. The initial conception of the dynamic strategy optimization module is to facilitate online learning and continuous optimization of agent decision-making capabilities. This objective is realized through the construction of a topology correlation matrix, which is based on microgrid operation data. The subsequent generation of preliminary control actions is facilitated by a multi-agent adaptive decision network. Concurrently, a safety optimization model founded upon the barrier Lyapunov function has been developed. The model has been designed to facilitate collaborative correction and safety constraint verification of the preliminary actions, thereby producing final control actions that satisfy global optimization and safe operation requirements. On this basis, an enhanced execution control module is employed, incorporating adaptive ramp rate limitations to calculate the target power reference, achieving high precision and fast tracking of power commands. The findings from both simulation and experimental studies demonstrate that, in complex scenarios such as load fluctuations and topology reconfiguration, the proposed method maintains voltage fluctuations within 1.6 V, achieves frequency recovery within 0.01 s, ensures a rapid power sharing response with a small steady-state error, and improves system operational economy by approximately 8.2% compared to conventional distributed control methods. This enhancement of dynamic adaptability, operational safety, and economic performance of the microgrid is therefore significant.
Open AccessOptimal Control Method for Microgrid Distributed Generation Based on Multi-Agent Adaptive Decision-Making
In addressing the challenges of strong power generation fluctuation, complex load variation, and dynamic topology changes in microgrid operation, this paper puts forward a proposal for optimal control methodology for distributed generation based on multi-agent adaptive decision-making. The initial conception of the dynamic strategy optimization module is to facilitate online learning and continuous optimization of agent decision-making capabilities. This objective is realized through the construction of a topology correlation matrix, which is based on microgrid operation data. The subsequent generation of preliminary control actions is facilitated by a multi-agent adaptive decision network. Concurrently, a safety optimization model founded upon the barrier Lyapunov function has been developed. The model has been designed to facilitate collaborative correction and safety constraint verification of the preliminary actions, thereby producing final control actions that satisfy global optimization and safe operation requirements. On this basis, an enhanced execution control module is employed, incorporating adaptive ramp rate limitations to calculate the target power reference, achieving high precision and fast tracking of power commands. The findings from both simulation and experimental studies demonstrate that, in complex scenarios such as load fluctuations and topology reconfiguration, the proposed method maintains voltage fluctuations within 1.6 V, achieves frequency recovery within 0.01 s, ensures a rapid power sharing response with a small steady-state error, and improves system operational economy by approximately 8.2% compared to conventional distributed control methods. This enhancement of dynamic adaptability, operational safety, and economic performance of the microgrid is therefore significant.
- Open Access
A Multi-Strategy Enhanced Whale Optimization Algorithm for Long Short-Term Memory—Application to Short-Term Power Load Forecasting for Microgrid Buildings
High-accuracy short-term electric load forecasting is essential for ensuring the security of power systems and enhancing energy efficiency. Power load sequences are characterized by strong randomness, non-stationarity, and nonlinearity over time. To improve the precision and efficiency of short-term load forecasting in microgrids, a hybrid predictive model combining Complementary Ensemble Empirical Mode Decomposition (CEEMD) and a multi-strategy enhanced Whale Optimization Algorithm (WOA) with Long Short-Term Memory (LSTM) neural networks has been proposed. Initially, this study employs CEEMD to decompose the short-term electric load time series. Subsequently, a multi-strategy enhanced WOA with chaotic initialization and reverse learning is introduced to enhance the search capability of model parameters and avoid entrapment in local optima. Finally, considering the distinct characteristics of each component, the multi-strategy improved WOA is utilized to optimize the LSTM model, establishing individual predictive models for each component, and the predictions are then aggregated. The proposed method’s forecasting accuracy has been validated through multiple case studies using the UC San Diego microgrid data, demonstrating its reliability and providing a solid foundation for microgrid system planning and stable operation.
Open AccessA Multi-Strategy Enhanced Whale Optimization Algorithm for Long Short-Term Memory—Application to Short-Term Power Load Forecasting for Microgrid Buildings
High-accuracy short-term electric load forecasting is essential for ensuring the security of power systems and enhancing energy efficiency. Power load sequences are characterized by strong randomness, non-stationarity, and nonlinearity over time. To improve the precision and efficiency of short-term load forecasting in microgrids, a hybrid predictive model combining Complementary Ensemble Empirical Mode Decomposition (CEEMD) and a multi-strategy enhanced Whale Optimization Algorithm (WOA) with Long Short-Term Memory (LSTM) neural networks has been proposed. Initially, this study employs CEEMD to decompose the short-term electric load time series. Subsequently, a multi-strategy enhanced WOA with chaotic initialization and reverse learning is introduced to enhance the search capability of model parameters and avoid entrapment in local optima. Finally, considering the distinct characteristics of each component, the multi-strategy improved WOA is utilized to optimize the LSTM model, establishing individual predictive models for each component, and the predictions are then aggregated. The proposed method’s forecasting accuracy has been validated through multiple case studies using the UC San Diego microgrid data, demonstrating its reliability and providing a solid foundation for microgrid system planning and stable operation.