Yonghui Li

Hybrid renewable energy sources and microgrids will determine future electricity generation and supply. Therefore, evaluating the uncertain intermittent output power is essential to building long-term sustainable and reliable microgrid operations to fulfill the growing energy demands. To address this, we proposed a robust mixed-integer linear programming model for the microgrid to minimize the day-ahead cost. To validate the proposed model piecewise linear curve is to deal with uncertainties of wind turbine, photovoltaic, and electrical load. The proposed solution is demonstrated through a case study compared under a robust worst-case scenario, deterministic model, and max–min robust optimization that aim to find optimal robustness. So, a piecewise linear curve is considered to obtain uncertain parameters in order to deal with uncertainties and predict the day-ahead cost. This study illustrates how the Uncertainty Budget Set selection used to integrate renewable energy sources into a microgrid, which manages the energy system. Therefore, the model complexity was slightly modified by adjusting the Uncertainty Budget Set to obtain the optimal decision and control the load demand and uncertainty of renewable energy sources. The comparative results demonstrate that the proposed robust optimization can achieve high solutions under microgrid’s availability and is intended to confirm that the proposed method is more cost-effective than alternative optimization techniques. Additionally, the effectiveness and advantage of the proposed methodology in the IEEE 33-node system are validated in this case study by comparing it to the existing optimization. The comparison results show that the proposed robust optimization methods illustrate the model’s efficiency, concluding remarks, and managerial insights of the research.

Due to the limited capacity of a single microgrid, multiple sub-microgrids form interconnected multi-microgrids. However, load variation, distributed power output uncertainty and multi-microgrids network complexity have brought great difficulties to the frequency stability of the whole microgrid. To address this problem, this paper uses a multi-agent deep reinforcement learning（DRL）algorithm to design the controllers to control the frequency of the multi-microgrids. Firstly, a Load Frequency Control (LFC) model for multi-microgrids was built for a single microgrid. Secondly, based on the Centralized Training and Decentralized execution (CTDE) multi-agent reinforcement learning (RL) framework, the Multi-Agent Soft Actor-Critic (MASAC) algorithm was designed and applied to the multi-microgrids model. The state space and action space of multi-agent were established according to the frequency deviation of every sub-microgrid and the output of each distributed power source. The reward function was then established according to the frequency deviation, and the frequency control problem was transformed into the reward maximization problem. The appropriate neural network and training parameters were selected to generate the interconnected microgrid controllers through multiple training of pre-learning. Finally, the simulation study shows that the MASAC controller proposed in this paper can quickly maintain frequency stability when the system is disturbed. The MASAC controller has strong adaptability and robustness under complex operating conditions whence the wind turbine is incapable of frequency regulation and the distribution network of the isolated system changes.