Day‐ahead forecasting of losses in the distribution network
- 1 June 2021
- journal article
- research article
- Published by Wiley in AI Magazine
- Vol. 42 (2), 38-49
- https://doi.org/10.1609/aimag.v42i2.15097
Abstract
Utility companies in the Nordics have to nominate how much electricity is expected to be lost in their power grid the next day. We present a commercially deployed machine learning system that automates this day-ahead nomination of the expected grid loss. 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 reduced the mean average percentage error (MAPE) with 40% from 12.17 to 7.26 per hour from mid-July to mid-October, 2019. It is robust, flexible and reduces manual work. Recently, the system was deployed to forecast and nominate grid losses for two new grids belonging to a new customer. As the presented system is modular and adaptive, the integration was quick and needed minimal work. We have shared the grid loss data-set on Kaggle.This publication has 12 references indexed in Scilit:
- Developing a Method to Account for Avoided Grid Losses from Decentralized Generation: the EU CaseEnergy Procedia, 2017
- Forecasting software for hourly transmission lossesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- The Challenge of Non-Technical Loss Detection Using Artificial Intelligence: A SurveyInternational Journal of Computational Intelligence Systems, 2017
- Forced renewables penetration impact on ohmic transmission lossesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Forecasting hourly corona losses applying statistical approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Mean Absolute Percentage Error for regression modelsNeurocomputing, 2016
- Improving the efficiency of power distribution systems through technical and non-technical losses reductionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- A Systematic Loss Analysis of Taipower Distribution SystemIEEE Transactions on Power Systems, 2006
- Distribution System Losses Evaluation by ANN ApproachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- A new method for the computation of technical losses in electrical power distribution systemsPublished by Institution of Engineering and Technology (IET) ,2001