Machine Learning Based Integrated Feature Selection Approach for Improved Electricity Demand Forecasting in Decentralized Energy Systems
Improved performance electricity demand forecast can provide decentralized energy system operators, aggregators, managers, and other stakeholders with essential information for energy resource scheduling, demand response management, and energy market participation. Most previous methodologies have f...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8744520/ |
| _version_ | 1818621725453058048 |
|---|---|
| author | Abinet Tesfaye Eseye Matti Lehtonen Toni Tukia Semen Uimonen R. John Millar |
| author_facet | Abinet Tesfaye Eseye Matti Lehtonen Toni Tukia Semen Uimonen R. John Millar |
| author_sort | Abinet Tesfaye Eseye |
| collection | DOAJ |
| description | Improved performance electricity demand forecast can provide decentralized energy system operators, aggregators, managers, and other stakeholders with essential information for energy resource scheduling, demand response management, and energy market participation. Most previous methodologies have focused on predicting the aggregate amount of electricity demand at national or regional scale and disregarded the electricity demand for small-scale decentralized energy systems (buildings, energy communities, microgrids, local energy internets, etc.), which are emerging in the smart grid context. Furthermore, few research groups have performed attribute selection before training predictive models. This paper proposes a machine learning (ML)-based integrated feature selection approach to obtain the most relevant and nonredundant predictors for accurate short-term electricity demand forecasting in distributed energy systems. In the proposed approach, one of the ML tools- binary genetic algorithm (BGA) is applied for the feature selection process and Gaussian process regression (GPR) is used for measuring the fitness score of the features. In order to validate the effectiveness of the proposed approach, it is applied to various building energy systems located in the Otaniemi area of Espoo, Finland. The findings are compared with those achieved by other feature selection techniques. The proposed approach enhances the quality and efficiency of the predictor selection, with minimal chosen predictors to achieve improved prediction accuracy. It outperforms the other evaluated feature selection methods. Besides, a feedforward artificial neural network (FFANN) model is implemented to evaluate the forecast performance of the selected predictor subset. The model is trained using two-year hourly dataset and tested with another one-year hourly dataset. The obtained results verify that the FFANN forecast model based on the BGA-GPR FS selected training feature subset has achieved an annual MAPE of 1.96%, which is a very acceptable and promising value for electricity demand forecasting in small-scale decentralized energy systems. |
| first_indexed | 2024-12-16T18:13:50Z |
| format | Article |
| id | doaj.art-7b13611bddb8494dbfda147bba737188 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T18:13:50Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7b13611bddb8494dbfda147bba7371882022-12-21T22:21:42ZengIEEEIEEE Access2169-35362019-01-017914639147510.1109/ACCESS.2019.29246858744520Machine Learning Based Integrated Feature Selection Approach for Improved Electricity Demand Forecasting in Decentralized Energy SystemsAbinet Tesfaye Eseye0https://orcid.org/0000-0001-7225-1819Matti Lehtonen1Toni Tukia2Semen Uimonen3R. John Millar4Department of Electrical Engineering and Automation, Aalto University, Espoo, FinlandDepartment of Electrical Engineering and Automation, Aalto University, Espoo, FinlandDepartment of Electrical Engineering and Automation, Aalto University, Espoo, FinlandDepartment of Electrical Engineering and Automation, Aalto University, Espoo, FinlandDepartment of Electrical Engineering and Automation, Aalto University, Espoo, FinlandImproved performance electricity demand forecast can provide decentralized energy system operators, aggregators, managers, and other stakeholders with essential information for energy resource scheduling, demand response management, and energy market participation. Most previous methodologies have focused on predicting the aggregate amount of electricity demand at national or regional scale and disregarded the electricity demand for small-scale decentralized energy systems (buildings, energy communities, microgrids, local energy internets, etc.), which are emerging in the smart grid context. Furthermore, few research groups have performed attribute selection before training predictive models. This paper proposes a machine learning (ML)-based integrated feature selection approach to obtain the most relevant and nonredundant predictors for accurate short-term electricity demand forecasting in distributed energy systems. In the proposed approach, one of the ML tools- binary genetic algorithm (BGA) is applied for the feature selection process and Gaussian process regression (GPR) is used for measuring the fitness score of the features. In order to validate the effectiveness of the proposed approach, it is applied to various building energy systems located in the Otaniemi area of Espoo, Finland. The findings are compared with those achieved by other feature selection techniques. The proposed approach enhances the quality and efficiency of the predictor selection, with minimal chosen predictors to achieve improved prediction accuracy. It outperforms the other evaluated feature selection methods. Besides, a feedforward artificial neural network (FFANN) model is implemented to evaluate the forecast performance of the selected predictor subset. The model is trained using two-year hourly dataset and tested with another one-year hourly dataset. The obtained results verify that the FFANN forecast model based on the BGA-GPR FS selected training feature subset has achieved an annual MAPE of 1.96%, which is a very acceptable and promising value for electricity demand forecasting in small-scale decentralized energy systems.https://ieeexplore.ieee.org/document/8744520/Binary genetic algorithmdecentralized energy systemelectricity demand forecastingfeature selectionfeedforward artificial neural networkfitness evaluation measure |
| spellingShingle | Abinet Tesfaye Eseye Matti Lehtonen Toni Tukia Semen Uimonen R. John Millar Machine Learning Based Integrated Feature Selection Approach for Improved Electricity Demand Forecasting in Decentralized Energy Systems IEEE Access Binary genetic algorithm decentralized energy system electricity demand forecasting feature selection feedforward artificial neural network fitness evaluation measure |
| title | Machine Learning Based Integrated Feature Selection Approach for Improved Electricity Demand Forecasting in Decentralized Energy Systems |
| title_full | Machine Learning Based Integrated Feature Selection Approach for Improved Electricity Demand Forecasting in Decentralized Energy Systems |
| title_fullStr | Machine Learning Based Integrated Feature Selection Approach for Improved Electricity Demand Forecasting in Decentralized Energy Systems |
| title_full_unstemmed | Machine Learning Based Integrated Feature Selection Approach for Improved Electricity Demand Forecasting in Decentralized Energy Systems |
| title_short | Machine Learning Based Integrated Feature Selection Approach for Improved Electricity Demand Forecasting in Decentralized Energy Systems |
| title_sort | machine learning based integrated feature selection approach for improved electricity demand forecasting in decentralized energy systems |
| topic | Binary genetic algorithm decentralized energy system electricity demand forecasting feature selection feedforward artificial neural network fitness evaluation measure |
| url | https://ieeexplore.ieee.org/document/8744520/ |
| work_keys_str_mv | AT abinettesfayeeseye machinelearningbasedintegratedfeatureselectionapproachforimprovedelectricitydemandforecastingindecentralizedenergysystems AT mattilehtonen machinelearningbasedintegratedfeatureselectionapproachforimprovedelectricitydemandforecastingindecentralizedenergysystems AT tonitukia machinelearningbasedintegratedfeatureselectionapproachforimprovedelectricitydemandforecastingindecentralizedenergysystems AT semenuimonen machinelearningbasedintegratedfeatureselectionapproachforimprovedelectricitydemandforecastingindecentralizedenergysystems AT rjohnmillar machinelearningbasedintegratedfeatureselectionapproachforimprovedelectricitydemandforecastingindecentralizedenergysystems |