基于XGBoost短期预测控制的微电网多时间尺度调度

MULTI-TIME SCALE SCHEDULING OF MICROGRID BASED ON XGBOOST SHORT-TERM PREDICTIVE CONTROL

针对交直流混合微电网中可再生能源发电不确定性导致的预测误差,提出一种基于XGBoost短期预测控制的多时间尺度调度策略。基于NSGA-II算法,结合风光出力与负荷的供需关系,优化和制定未来24小时的调度计划;针对预测误差产生的功率波动,引入XGBoost短期预测模型,实现对日前调度的实时修正。以中国北方某小区供电系统为例进行验证,并分析不同直流负荷比例对优化调度结果的影响,结果表明该方法可以有效提高微电网运行效益及稳定性。

Aiming at the prediction error caused by the uncertainty of renewable energy generation in AC/DC hybrid microgrid,a multi-time scale scheduling strategy based on XGBoost short-term predictive control is proposed.Based on the NSGA-II algorithm,combined with the supply and demand relationship of wind power output and load,proposed method to optimize and formulate the scheduling plan for the next 24 hours.According to the power fluctuation caused by the prediction error,we introduced the XGBoost short-term prediction model to realize real-time correction of the daily scheduling.The power supply system in a residential area in northern China was taken as an example to verify the impact of different DC load ratios on the optimal scheduling results.The results show that the proposed method can effectively improve the efficiency and stability of the microgrid.