基于人工蜂群优化极限学习机的短期负荷预测

Short-term load forecasting based on improved extreme learning machine with artificial bee colony algorithm

针对极限学习机(Extreme Learning Machine,ELM)在训练前随机产生输入层权值和隐含层阈值导致输出结果不稳定,影响短期负荷预测精度的缺陷,提出基于人工蜂群(Artificial Bee Colony,ABC)算法改进ELM(ABC-ELM)的短期负荷预测新方法。首先,选用历史负荷、外界气象因素和待预测日星期类型等属性构成ELM输入向量,以负荷值为输出,构建ELM模型;其次,采用ABC对ELM输入层权值和隐含层阈值进行优化;最后,根据优化参数,建立基于ABC-ELM的负荷预测模型,并以该模型开展负荷预测。根据国内某大型城市实测负荷数据开展实验,验证方法有效性。实验结果证明ABC-ELM较ELM和BP神经网络具有更高的稳定性和预测精度。

Extreme learning machine （ELM） with random input weights and hidden biases may lead to unstable performance and low prediction accuracy. This paper proposes a new short-term load forecasting method based on artificial bee colony （ABC） algorithm and ELM （ABC-ELM）. Firstly, historical load, meteorological factor and day of week are selected as input variables to build the ELM model. Secondly, optimal input weights and hidden biases of ELM are selected by ABC algorithm. Finally, the new model of load forecasting with optimized parameters is constructed based on ABC-ELM. The real load date from a large city in China is applied to estimate the performance of proposed method. Experiment results show that the new method has higher stability and accuracy than ELM and BP neural networks.