摘要
因电力系统的复杂性和不确定性,建立了一种自适应灰色分数加权模型来预测某省的用电量,有效提高了用电量的预测精度。模型引入分数加权系数来设计新的初始条件,与传统灰色模型相比,新的初始条件能够动态捕捉用电信息特性方面的优势。此外,为了进一步提高预测精度,利用粒子群算法(PSO)估计了初始条件的加权系数和相应的时间参数,并对比了5个预测模型的结果,验证了模型的有效性。试验结果表明,模型在用电量预测中表现出了良好的性能,能更好地利用所有数据信息。
Due to the complexity and uncertainty of the power system,an adaptive gray score weighted model was established to predict the electricity consumption of a certain province,which effectively improved the accuracy of electricity consumption prediction.In this model,a score weighting coefficient was introduced to design new initial conditions.Compared with the traditional gray model,the new initial conditions can dynamically capture the advantages of electricity consumption information characteristics.In addition,in order to further improve the prediction accuracy,the particle swarm algorithm(PSO)was used to estimate the weighting coefficients of the initial conditions and the corresponding time parameters,and the results of five prediction models were compared to verify the effectiveness of the models.The test results show that the model has shown good performance in electricity consumption prediction and can make better use of all data information.
作者
林琳
高雪
甄钊
Lin Lin;Gao Xue;Zhen Zhao(Baoding Technical College of Electric Power,Skills Training Center of State Grid Jibei Electric Power Co.,Ltd.,Baoding Hebei 071051,China;North China Electric Power University,Baoding Hebei 071003,China)
出处
《电气自动化》
2022年第3期34-37,共4页
Electrical Automation
关键词
灰色预测模型
用电量预测
粒子群算法
自适应
电力消费
grey prediction model
electricity consumption prediction
particle swarm algorithm(PSO)
adaptive
power consumption
