Using Machine Learning for the Optimisation of Operations and Management in Electric Systems and Networks

Aug 4, 2026

Upload by Ivy

This research applies a Random Forest machine learning model to predict electricity consumption and detect anomalies in electrical networks. Historical consumption data, weather conditions, and network events are used to forecast demand while addressing energy-sector challenges such as supply reliability and renewable integration. Data cleansing and normalisation precede training, with hyperparameters tuned via cross-validation. Results demonstrate accurate daily consumption prediction in a small town, achieving MAE of 198.73 MWh and R² of 0.9387.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

Introduction

Theoretical foundations

Load forecasting

Optimisation of generation and distribution

Reliability and diagnostics

Integration of renewable energy sources

Using machine learning for the optimisation of operations and management in electric systems and networks Semen Levin1* 1Tomsk State University of Control Systems and Radioelectronics, 40, prospect Lenina, Tomsk, 634050, Russia Abstract. This research employs the Random Forest Machine Learning model to predict electricity consumption and detect anomalies in electrical networks. Addressing the energy sector's challenges, such as supply reliability and renewable energy integration, this model processes historical electricity consumption data, weather conditions, and network events to efficiently forecast demand and identify anomalies. Data cleansing and normalisation preceded the training phase, where the model was fine-tuned using historical data to balance forecast accuracy andoverfitting avoidance. The dataset was divided into training (80%) and testing (20%) sets for performance evaluation. Through cross-validation, optimal model hyperparameters were determined. The findings highlight the model's efficacy in accurately predicting daily electricity consumption in a small, homogenous town. The model achieved a Mean Absolute Error (MAE) of 198.73 MWh and a coefficient of determination (R²) of 0.9387. Temperature, humidity, and wind speed were identified as key influencing factors on consumption levels. Conclusively, the Random Forest model presents a valuable tool for energy management, offering precise consumption forecasting and anomaly detection capabilities. Future work will address computational demands and enhance model integration with other Machine Learning methods for improved performance. This contribution is significant for efficient energy system planning and operation. 1 Introduction The contemporary world is on the cusp of significant changes in electrical power management. The increase in population, urbanisation, and technological progress pose new challenges to power systems. Among these are ensuring supply reliability, optimising expenses, and integrating renewable energy sources. In this segment, particular attention is paid to the application of Machine Learning (ML) to enhance electric networks [1] . Historically, power supply systems evolved towards increasing capacity and expanding networks. However, current realities demand a transition to more nuanced and flexible management, where big data analysis and automation play crucial roles. With its capability * Corresponding author: [semen.m.levin@tusur.ru](semen.m.levin@tusur.ru) © The Authors, published by EDP Sciences. This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0 ([https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)). to process vast amounts of information and identify patterns within the data, Machine Learning appears to be an ideal tool for achieving these objectives [2] . In recent years, significant progress has been observed in research and developments to incorporate ML into the energy sector. It includes forecasting electricity consumption [3], optimising power plant and substation operations, fault detection and anomaly identification in network operations, and managing energy flow to integrate decentralised sources [4, 5] . Despite the clear prospects, integrating ML into the energy infrastructure faces several issues. These include real-time data collection and processing difficulties, the need to adapt existing energy systems to new technologies, and security and data privacy concerns. Furthermore, an important aspect is developing algorithms capable of operating under uncertainty and changing input data. The research described in this article is focused on exploring the capabilities of machine learning for addressing pressing issues in the energy sector. Special attention is given to forecasting, analysis, and management within the context of smart electric grids. The primary applications of ML in the energy sector inc

FAQs

What machine learning approach is used in this research?

The study uses a Random Forest machine learning model.

Which data sources are used to predict electricity consumption and anomalies?

It processes historical electricity consumption data, weather conditions, and network events.

What performance metrics are reported for the model?

The model reports a Mean Absolute Error (MAE) of 198.73 MWh and a coefficient of determination (R²) of 0.9387.

Aug 4, 2026

Upload by Ivy