A Unified Energy Management Framework for Multi-Timescale Forecasting in Smart Grids
This work addresses the challenge of multi-timescale forecasting for power system management, which is crucial for implementing smart grid strategies like demand response, but it appears incremental as it builds on existing rolling optimization methods with a new architectural component.
The paper tackles the problem of accurately forecasting electrical load across multiple timescales in smart grids, proposing a novel framework called Multi-pofo that uses temporal positional encoding to capture mid- and long-term dependencies, and it outperforms strong baselines on real-world data.
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.