Big Data Analytics for Short and Medium-Term Electricity Load Forecasting Using an AI Techniques Ensembler
Electrical load forecasting provides knowledge about future consumption and generation of electricity. There is a high level of fluctuation behavior between energy generation and consumption. Sometimes, the energy demand of the consumer becomes higher than the energy already generated, and vice vers...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/13/19/5193 |
| _version_ | 1827704816054304768 |
|---|---|
| author | Nasir Ayub Muhammad Irfan Muhammad Awais Usman Ali Tariq Ali Mohammed Hamdi Abdullah Alghamdi Fazal Muhammad |
| author_facet | Nasir Ayub Muhammad Irfan Muhammad Awais Usman Ali Tariq Ali Mohammed Hamdi Abdullah Alghamdi Fazal Muhammad |
| author_sort | Nasir Ayub |
| collection | DOAJ |
| description | Electrical load forecasting provides knowledge about future consumption and generation of electricity. There is a high level of fluctuation behavior between energy generation and consumption. Sometimes, the energy demand of the consumer becomes higher than the energy already generated, and vice versa. Electricity load forecasting provides a monitoring framework for future energy generation, consumption, and making a balance between them. In this paper, we propose a framework, in which deep learning and supervised machine learning techniques are implemented for electricity-load forecasting. A three-step model is proposed, which includes: feature selection, extraction, and classification. The hybrid of Random Forest (RF) and Extreme Gradient Boosting (XGB) is used to calculate features’ importance. The average feature importance of hybrid techniques selects the most relevant and high importance features in the feature selection method. The Recursive Feature Elimination (RFE) method is used to eliminate the irrelevant features in the feature extraction method. The load forecasting is performed with Support Vector Machines (SVM) and a hybrid of Gated Recurrent Units (GRU) and Convolutional Neural Networks (CNN). The meta-heuristic algorithms, i.e., Grey Wolf Optimization (GWO) and Earth Worm Optimization (EWO) are applied to tune the hyper-parameters of SVM and CNN-GRU, respectively. The accuracy of our enhanced techniques CNN-GRU-EWO and SVM-GWO is 96.33% and 90.67%, respectively. Our proposed techniques CNN-GRU-EWO and SVM-GWO perform 7% and 3% better than the State-Of-The-Art (SOTA). In the end, a comparison with SOTA techniques is performed to show the improvement of the proposed techniques. This comparison showed that the proposed technique performs well and results in the lowest performance error rates and highest accuracy rates as compared to other techniques. |
| first_indexed | 2024-03-10T15:49:32Z |
| format | Article |
| id | doaj.art-3674e8ccb1ef4a05b5105b617a869d69 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T15:49:32Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-3674e8ccb1ef4a05b5105b617a869d692023-11-20T16:08:42ZengMDPI AGEnergies1996-10732020-10-011319519310.3390/en13195193Big Data Analytics for Short and Medium-Term Electricity Load Forecasting Using an AI Techniques EnsemblerNasir Ayub0Muhammad Irfan1Muhammad Awais2Usman Ali3Tariq Ali4Mohammed Hamdi5Abdullah Alghamdi6Fazal Muhammad7Department of Computer Science, Federal Urdu University of Arts, Science and Technology, Islamabad 44000, PakistanElectrical Engineering Department, College of Engineering, Najran University, Najran 61441, Saudi ArabiaSchool of Computing and Communications, Lancaster University, Bailrigg, Lancaster LA1 4YW, UKDepartment of Computing, RIPHAH University Faisalabad, Faisalabad 38000, PakistanElectrical Engineering Department, College of Engineering, Najran University, Najran 61441, Saudi ArabiaCollege of Computer Science and Information Systems, Najran University, Najran 61441, Saudi ArabiaCollege of Computer Science and Information Systems, Najran University, Najran 61441, Saudi ArabiaDepartment of Electrical Engineering, City University of Science & Information Technology Peshawar, Peshawar 25000, PakistanElectrical load forecasting provides knowledge about future consumption and generation of electricity. There is a high level of fluctuation behavior between energy generation and consumption. Sometimes, the energy demand of the consumer becomes higher than the energy already generated, and vice versa. Electricity load forecasting provides a monitoring framework for future energy generation, consumption, and making a balance between them. In this paper, we propose a framework, in which deep learning and supervised machine learning techniques are implemented for electricity-load forecasting. A three-step model is proposed, which includes: feature selection, extraction, and classification. The hybrid of Random Forest (RF) and Extreme Gradient Boosting (XGB) is used to calculate features’ importance. The average feature importance of hybrid techniques selects the most relevant and high importance features in the feature selection method. The Recursive Feature Elimination (RFE) method is used to eliminate the irrelevant features in the feature extraction method. The load forecasting is performed with Support Vector Machines (SVM) and a hybrid of Gated Recurrent Units (GRU) and Convolutional Neural Networks (CNN). The meta-heuristic algorithms, i.e., Grey Wolf Optimization (GWO) and Earth Worm Optimization (EWO) are applied to tune the hyper-parameters of SVM and CNN-GRU, respectively. The accuracy of our enhanced techniques CNN-GRU-EWO and SVM-GWO is 96.33% and 90.67%, respectively. Our proposed techniques CNN-GRU-EWO and SVM-GWO perform 7% and 3% better than the State-Of-The-Art (SOTA). In the end, a comparison with SOTA techniques is performed to show the improvement of the proposed techniques. This comparison showed that the proposed technique performs well and results in the lowest performance error rates and highest accuracy rates as compared to other techniques.https://www.mdpi.com/1996-1073/13/19/5193load forecastingoptimization techniquesdeep learningbig data analytics |
| spellingShingle | Nasir Ayub Muhammad Irfan Muhammad Awais Usman Ali Tariq Ali Mohammed Hamdi Abdullah Alghamdi Fazal Muhammad Big Data Analytics for Short and Medium-Term Electricity Load Forecasting Using an AI Techniques Ensembler Energies load forecasting optimization techniques deep learning big data analytics |
| title | Big Data Analytics for Short and Medium-Term Electricity Load Forecasting Using an AI Techniques Ensembler |
| title_full | Big Data Analytics for Short and Medium-Term Electricity Load Forecasting Using an AI Techniques Ensembler |
| title_fullStr | Big Data Analytics for Short and Medium-Term Electricity Load Forecasting Using an AI Techniques Ensembler |
| title_full_unstemmed | Big Data Analytics for Short and Medium-Term Electricity Load Forecasting Using an AI Techniques Ensembler |
| title_short | Big Data Analytics for Short and Medium-Term Electricity Load Forecasting Using an AI Techniques Ensembler |
| title_sort | big data analytics for short and medium term electricity load forecasting using an ai techniques ensembler |
| topic | load forecasting optimization techniques deep learning big data analytics |
| url | https://www.mdpi.com/1996-1073/13/19/5193 |
| work_keys_str_mv | AT nasirayub bigdataanalyticsforshortandmediumtermelectricityloadforecastingusinganaitechniquesensembler AT muhammadirfan bigdataanalyticsforshortandmediumtermelectricityloadforecastingusinganaitechniquesensembler AT muhammadawais bigdataanalyticsforshortandmediumtermelectricityloadforecastingusinganaitechniquesensembler AT usmanali bigdataanalyticsforshortandmediumtermelectricityloadforecastingusinganaitechniquesensembler AT tariqali bigdataanalyticsforshortandmediumtermelectricityloadforecastingusinganaitechniquesensembler AT mohammedhamdi bigdataanalyticsforshortandmediumtermelectricityloadforecastingusinganaitechniquesensembler AT abdullahalghamdi bigdataanalyticsforshortandmediumtermelectricityloadforecastingusinganaitechniquesensembler AT fazalmuhammad bigdataanalyticsforshortandmediumtermelectricityloadforecastingusinganaitechniquesensembler |