摘要
用户侧微电网负荷随机性强,短期负荷的预测精度对微电网的正常运行起着重要作用。提出了一种基于互补集成经验模态分解(CEEMD)和区域划分自适应变异粒子群(RSVPSO)算法优化核极限学习机(KELM)的负荷预测模型。采用互补集成经验模态分解将负荷序列分解为多组平稳的子序列,以减小不同局部信息之间的相互影响。针对粒子群算法易早熟和收敛速度慢的问题,利用区域划分来实现惯性权重和学习因子的自适应调整,提高粒子的全局寻优能力和搜索效率,并结合自适应变异操作避免陷入局部最优,加强核极限学习机预测精度。最后通过案例验证,所提模型的预测准确率约为98.114%,较其他预测模型具有更好的预测效果和实际应用意义。
Prediction accuracy of short-term load is critical to the normal operation of the micro-grid due to the strong load randomness of user-side micro-grid.A prediction model of kernel extreme learning machine(KELM)based on complementary ensemble empirical mode decomposition(CEEMD)and regional-division self-adapting variation particle swarm optimization(RSVPSO)is proposed in this paper.The load sequence is decomposed into several smooth subsequences by using complementary ensemble empirical mode decomposition to reduce the mutual influences among different local information.Aiming at the problem that particle swarm optimization is easy to fall into precocity and is slow in converge,an inertial weight and learning factor based on regional-division are utilized to improve the global search ability and search efficiency.Furthermore,combining with the adaptive mutation operation,the prediction accuracy of the kernel extreme learning machine is enhanced,yet the problem falling into the local optimum is avoided.Finally,the model proposed in this paper can obtain good performance of accuracy rate about 98.114%,which has better prediction effect and practical application significance than other prediction models.
作者
杜涵潇
汤旻安
Du Hanxiao;Tang Min′an(School of Automation and Electrical Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China)
出处
《电测与仪表》
北大核心
2020年第18期69-76,共8页
Electrical Measurement & Instrumentation
基金
国家自然科学基金资助项目(61663021
61763025
61861025)。
关键词
用户侧微电网
短期负荷预测
互补集成经验模态分解
核极限学习机
欧氏距离
自适应变异
粒子群算法
user-side micro-grid
short-term load forecasting
complementary ensemble empirical mode decomposition
kernel extreme learning machine
Euclidean metric
adaptive mutation
particle swarm optimization
