基于粒子群优化的非线性灰色Bernoulli模型在中长期负荷预测中的应用

Application of Particle Swarm Optimization Based Nonlinear Grey Bernoulli Model in Medium-and Long-Term Load Forecasting

将非线性灰色Bernoulli模型用于到中长期电力负荷预测,提出了优选模型参数的粒子群优化算法。该模型是将GM(1,1)模型与Bernoulli微分方程相结合的一种灰色模型,适用于对不同发展趋势曲线的预测。通过粒子群优化算法,以模型预测平均绝对百分误差最小为目标,选择最优的模型参数。采用不同测试数据以及实际电网负荷数据进行了验证,结果表明上述模型有很好的适应性及较高的预测精度。

In this paper, the nonlinear grey Bernoulli model （NGBM） is applied to medium- and long-term power load forecasting and a particle swarm optimization （PSO） algorithm to optimize the parameter of NGBM is proposed. The NGBM is a novel grey forecasting model integrating GM（1,1） model with Bernoulli differential equation and is suitable to the forecasting of various developing trend curves. By means of PSO and taking the minimum mean absolute percentage error of the forecasting model as objective function, the optimal model parameters are chosen. The proposed method is verified by different testing data and power load data of actual power system, thus it is proved that the proposed method possesses good adaptability and high forecasting accuracy.