Spatio-temporal Granularity Co-optimization Based Monthly Electricity Consumption Forecasting
CSEE Journal of Power and Energy Systems(2023)
摘要
Monthly electricity consumption forecasting (ECF) plays an important role in power system operation and electricity market trading. Widespread popularity of smart meters enables collection of fine-grained load data, which provides an opportunity for improvement of monthly ECF accuracy. In this letter, a spatio-temporal granularity co-optimization-based monthly ECF framework is proposed, which aims to find an optimal combination of temporal granularity and spatial clusters to improve monthly ECF accuracy. The framework is formulated as a nested bi-layer optimization problem. A grid search method combined with a greedy clustering method is proposed to solve the optimization problem. Superiority of the proposed method has been verified on a real smart meter dataset.
更多查看译文
关键词
Electricity consumption forecasting,Greedy clustering,Grid searching,Spatiotemporal
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要