Day-Ahead Forecasting of Losses in the Distribution Network

Abstract

We present a commercially deployed machine learning system that automates the day-ahead nomination of the expected grid loss for a Norwegian utility company. It meets several practical constraints and issues related to, among other things, delayed, missing and incorrect data and a small data set. The system incorporates a total of 24 different models that performs forecasts for three sub-grids. Each day one model is selected for making the hourly day-ahead forecasts for each sub-grid. The deployed system reduces the MAE with 41% from 3.68 MW to 2.17 MW per hour from mid July to mid October. It is robust and reduces manual work.

Cite

Text

Dalal et al. "Day-Ahead Forecasting of Losses in the Distribution Network." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I08.7018

Markdown

[Dalal et al. "Day-Ahead Forecasting of Losses in the Distribution Network." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/dalal2020aaai-day/) doi:10.1609/AAAI.V34I08.7018

BibTeX

@inproceedings{dalal2020aaai-day,
  title     = {{Day-Ahead Forecasting of Losses in the Distribution Network}},
  author    = {Dalal, Nisha and Mølnå, Martin and Herrem, Mette and Røen, Magne and Gundersen, Odd Erik},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {13148-13155},
  doi       = {10.1609/AAAI.V34I08.7018},
  url       = {https://mlanthology.org/aaai/2020/dalal2020aaai-day/}
}