Analysis for Non-Residential Short-Term Load Forecasting Using Machine Learning and Statistical Methods with Financial Impact on the Power Market

Stefan Ungureanu, Vasile Topa and Andrei Cristinel Cziker
Additional contact information
Stefan Ungureanu: Department of Electric Power Systems and Management, Technical University of Cluj Napoca, 26-28 Baritiu, 400114 Cluj Napoca, Romania
Vasile Topa: Department of Electrotechnics and Measurements, Technical University of Cluj Napoca, 26-28 Baritiu, 400114 Cluj Napoca, Romania
Andrei Cristinel Cziker: Department of Electric Power Systems and Management, Technical University of Cluj Napoca, 26-28 Baritiu, 400114 Cluj Napoca, Romania

Energies, 2021, vol. 14, issue 21, 1-26

Abstract: Short-term load forecasting predetermines how power systems operate because electricity production needs to sustain demand at all times and costs. Most load forecasts for the non-residential consumers are empirically done either by a customer’s employee or supplier personnel based on experience and historical data, which is frequently not consistent. Our objective is to develop viable and market-oriented machine learning models for short-term forecasting for non-residential consumers. Multiple algorithms were implemented and compared to identify the best model for a cluster of industrial and commercial consumers. The article concludes that the sliding window approach for supervised learning with recurrent neural networks can learn short and long-term dependencies in time series. The best method implemented for the 24 h forecast is a Gated Recurrent Unit (GRU) applied for aggregated loads over three months of testing data resulted in 5.28% MAPE and minimized the cost with 5326.17 € compared with the second-best method LSTM. We propose a new model to evaluate the gap between evaluation metrics and the financial impact of forecast errors in the power market environment. The model simulates bidding on the power market based on the 24 h forecast and using the Romanian day-ahead market and balancing prices through the testing dataset.

Keywords: load forecasting; machine learning; power market; forecast evaluation (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.mdpi.com/1996-1073/14/21/6966/pdf (application/pdf)
https://www.mdpi.com/1996-1073/14/21/6966/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:14:y:2021:i:21:p:6966-:d:663032

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().