基于模糊插值模型的短期负荷预测

Short-term Load Forecasting Based on Fuzzy Interpolation Modeling

针对隶属函数对模糊推理模型描述性能和精度的影响,为了进一步提高模糊插值模型的泛化能力,提出了一类参数可调隶属函数,调整其参数从而可改变函数的形状,使之能逼近常用的三角形、高斯型等隶属函数。用它作为插值函数,提出了基于参数可调隶属函数的模糊插值模型,利用粒子群优化算法(PSO)优化模型中参数,并将该模型应用于电力系统的短期负荷预测中,仿真结果证明了该模型的有效性。

Considering the effect of interpolation function on performance and precision of the fuzzy modeling, a class of parameters adjustable interpolation function was designed in order to enhance the generalization ability of fuzzy interpolation model. The shape of the interpolation function was changed by adjusting the parameters so that it could close to such as type of the triangle and Gaussian membership function. The fuzzy modeling based on parameters adjustable interpolation function was designed. Particle Swarm Optimization （PSO） algorithm was adopted to optimize the model parameters. By applying the model to power system short-term load forecasting, the simulation shows the effective of the model.