A Unified Energy Management Framework for Multi-Timescale Forecasting in Smart Grids

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Dafang, Piao, Xihao, Chen, Zheng, Li, Zhengmao, Taniguchi, Ittetsu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909400848924672
author Zhao, Dafang
Piao, Xihao
Chen, Zheng
Li, Zhengmao
Taniguchi, Ittetsu
author_facet Zhao, Dafang
Piao, Xihao
Chen, Zheng
Li, Zhengmao
Taniguchi, Ittetsu
contents Accurate forecasting of the electrical load, such as the magnitude and the timing of peak power, is crucial to successful power system management and implementation of smart grid strategies like demand response and peak shaving. In multi-time-scale optimization scheduling, rolling optimization is a common solution. However, rolling optimization needs to consider the coupling of different optimization objectives across time scales. It is challenging to accurately capture the mid- and long-term dependencies in time series data. This paper proposes Multi-pofo, a multi-scale power load forecasting framework, that captures such dependency via a novel architecture equipped with a temporal positional encoding layer. To validate the effectiveness of the proposed model, we conduct experiments on real-world electricity load data. The experimental results show that our approach outperforms compared to several strong baseline methods.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15254
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Unified Energy Management Framework for Multi-Timescale Forecasting in Smart Grids
Zhao, Dafang
Piao, Xihao
Chen, Zheng
Li, Zhengmao
Taniguchi, Ittetsu
Machine Learning
Artificial Intelligence
Accurate forecasting of the electrical load, such as the magnitude and the timing of peak power, is crucial to successful power system management and implementation of smart grid strategies like demand response and peak shaving. In multi-time-scale optimization scheduling, rolling optimization is a common solution. However, rolling optimization needs to consider the coupling of different optimization objectives across time scales. It is challenging to accurately capture the mid- and long-term dependencies in time series data. This paper proposes Multi-pofo, a multi-scale power load forecasting framework, that captures such dependency via a novel architecture equipped with a temporal positional encoding layer. To validate the effectiveness of the proposed model, we conduct experiments on real-world electricity load data. The experimental results show that our approach outperforms compared to several strong baseline methods.
title A Unified Energy Management Framework for Multi-Timescale Forecasting in Smart Grids
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2411.15254