An Image Inpainting Approach to Short-Term Load Forecasting

• Published in: IEEE transactions on power systems 2023-01, Vol.38 (1), p.177-187
• Main Authors: Liu, Yanzhu, Dutta, Shreya, Kong, Adams Wai Kin, Yeo, Chai Kiat
• Format: Article
• Language: English
• Subjects: Deep learning; Electrical loads; Feature extraction; Forecasting; Image processing; Load forecasting; Load modeling; Neighborhoods; Neural networks; Predictive models; Recurrent neural networks; short-term load forecasting; Three-dimensional displays; univariate time-series
• ISSN: 0885-8950; 1558-0679
• DOI: 10.1109/TPWRS.2022.3159493

In current power systems, electrical energy is generated whenever there is a demand for it. Therefore, load forecasting, which estimates the active load in advance, is imperative for power system planning and operations. Based on the time horizon, load forecasting is classified as very short-term (below one day), short-term (a day to two weeks), medium-term (two weeks to three years) and long-term (over three years). This paper focuses on the short-term forecasting. The complex multi-level seasonality of load series (e.g., the load in a given hour is not only dependent on load in the previous hour, but also on the previous day.s load in the same hour, and on the previous week's load in the same day-of-the-week and hour) makes this task challenging, especially when the load data is represented in 1d numerical series. However, in multi-channel images, the patterns in spatial neighbourhood of one channel and the patterns in the neighbourhood along the channel dimension are able to be captured by 3d image processing operations. Hence, this study proposes to transform electrical load data from 1d series to 3d images and transform the problem from future series forecasting to missing patch inpainting. Furthermore, it proposes a recurrent neural network to model the temporal trends in the series by convolutional operations on the spatial neighbourhood in the images. Experimental results demonstrate the effectiveness of the proposed method on two benchmarks and show the capability of inferring the future load from related series if there is a lack of history.