自回归误差下的改进Lyapounov最大指数法在短期负荷预测中的应用研究

An improved lyapounov biggest index method in the research of short-term load forecasting

电力系统在国民经济发展中具有重要地位,保持电网的供需平衡是电力系统稳定运行的基础。由于当前的超大容量存储技术发展的还不够成熟,难以解决剩余电能的存储问题,所以,目前电能供给与需求还必须遵循供需平衡的原则。为了对供电系统日前调度进行更好的优化,针对Lyapounov最大指数法的嵌入维数提出了一个自回归误差算法,该算法克服了以往人为对嵌入维数进行取值造成的维数获取不准确问题。同时,提出的回归算法模型还可以解决人为因素造成的预测误差较大且误差具有随机性问题。因此,采用我们提出的算法进行负荷预测,能够使得电网发电机组备用计划制定更加合理,从而可以减少发电机组由于备用不合理带来的经济损失。最后,通过仿真对比分析可以得出采用本算法的相空间重构电力负荷短期预测值更加接近于真实值,而且得到的误差范围更小更稳定。同时,由仿真结果也验证了所提算法模型的有效性和可行性。

Power system plays an important role in the development of national economy, and maintaining the balance between supply and demand of power network is the foundation of the stable operation of power system. As the current super-capacity storage technology is not mature enough to solve the storage problem of residual power, the current power supply and demand must follow the principle of balance between supply and demand. In order to better optimize the day-ahead scheduling problem of power supply system, an auto-regression error algorithm for embedding dimension of Lyapounov maximum index method is proposed. The algorithm model overcomes the inaccuracy caused by the artificial value of embedded dimension in the past. At the same time, it also solves the problem of large prediction error caused by human factors and the randomness of error. Therefore, the algorithm proposed in this paper makes the backup plan of grid generator set more reasonable, and reduces the economic loss of generator set caused by unreasonable backup. Finally, through the comparison and analysis, the results showed that the short-term predicted value of the phase-space reconstruction power load using this algorithm is closer to the real value, and the error range is smaller and more stable. Meanwhile, the effectiveness and feasibility of the proposed algorithm model are also verified.