基于自回归积分滑动平均模型的可转移负荷竞价策略

Bidding Strategy for Time-shiftable Loads Based on Autoregressive Integrated Moving Average Model

研究了在较成熟的电力市场环境下,可转移负荷在日前市场和实时市场的最优竞价策略。在最优报价计算过程中,必须满足可转移负荷在截止时间内完成运行一定的电能消耗的约束条件。考虑到传统平均值短期负荷预测结果存在偏差,提出了一种基于自回归积分滑动平均模型的可转移负荷最优竞价策略,通过历史电价的变化特征估计模型的参数,从而预测第二天的日前电价和实时电价曲线,并以此为依据优化竞价策略。在此基础上,考虑功率限制,提出了基于贪心算法思想的电能竞价自动调整算法。通过实际电价数据进行计算,验证了此策略比单纯利用历史数据的期望值作为模型参数为购电者节省了更多购电费用,并能够有效完成竞价调整,以满足各个周期的功率限制。

The optimal bidding strategy for time-shiftable loads in the day-ahead market and real-time market is studied respectively in an advanced power market environment.In the bidding optimization,it must be guaranteed that the timeshiftable loads consume a certain amount of electricity within deadline.Considering the deviation of short-term load forecasting results of the traditional average value method,an autoregressive integrated moving average(ARIMA)model is proposed to analyze the optimal bidding strategy for time-shiftable loads.The model parameters are estimated by the characteristics of historical electricity price,so as to predict the price curve of the day-ahead price and the real-time price on the second day,based on which the bidding strategy is optimized.Then,agreedy algorithm is proposed to adjust the energy bidding considering the power usage limit in each period.Finally,the proposed method is verified by a case study,which shows that the method can help save more energy procurement cost than the methods simply using the expected value of historical data as parameters,and adjust the energy bidding effectively according to the power usage limit as well.