论文部分内容阅读
提出了一种基于果蝇优化算法(FOA)和最小二乘支持向量机(LSSVM)模型的日均电价混合预测模型。将日均电价的历史数据和负荷数据作为输入变量,利用FOA优化选择用于电价预测的LSSVM模型最优参数值,进而对日均电价进行预测。以澳大利亚NSW电力市场的实际数据为例对该模型进行了仿真测试,其结果表明:与自适应LSSVM、模拟退火LSSVM和ARIMA-GARCH模型相比,本文提出的预测模型的预测性能最好,其收敛速度快,预测精度高。
This paper presents a daily average price mixed forecasting model based on fruit fly optimization algorithm (FOA) and least square support vector machine (LSSVM) model. The daily average price of electricity historical data and load data as input variables, the use of FOA optimization selection for electricity price forecast LSSVM optimal parameter values, and then the average daily price forecast. The simulation results show that the prediction model proposed in this paper has the best performance compared with the adaptive LSSVM, the simulated annealing LSSVM and the ARIMA-GARCH model Fast convergence, high prediction accuracy.