基于自适应粒子群参数优化的最小二乘支持向量机用电量预测模型

为应对当前复杂非线性的宏观经济形势与电力消耗情况,本文提出了一种自适应粒子群算法改进的最小二乘支持向量机负荷预测模型。根据粒子群中粒子的成熟程度对其进行分类,对不同类别的粒子分别采取不同的位置更新方式,可以保持粒子种群多样性,避免造成局部最优。利用自适应粒子群算法优化最小二乘支持向量机的模型参数,经过实证分析能够一定程度提高模型的预测精度,可以为中长期负荷预测工作提供一些的参考。

Power consumption prediction model of least squares support vector machine based on adaptive particle swarm optimization

In order to cope with the current complex nonlinear macroeconomic situation and power consumption, this paper proposes an improved least squares support vector machine load forecasting model based on adaptive particle swarm optimization. According to the maturity of the particles in the particle group, different position updating methods are adopted for different types of particles, which can maintain the diversity of the particle population and avoid local optimization. The adaptive particle swarm optimization algorithm is used to optimize the model parameters of the least squares support vector machine. After empirical analysis, the prediction accuracy of the model can be improved to some extent, which can provide some reference for medium and long-term load forecasting.