Hybrid Short-Term Load Forecasting Scheme Using Random Forest and Multilayer Perceptron
A stable power supply is very important in the management of power infrastructure. One of the critical tasks in accomplishing this is to predict power consumption accurately, which usually requires considering diverse factors, including environmental, social, and spatial-temporal factors. Depending...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-11-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/11/12/3283 |
| _version_ | 1811263262036066304 |
|---|---|
| author | Jihoon Moon Yongsung Kim Minjae Son Eenjun Hwang |
| author_facet | Jihoon Moon Yongsung Kim Minjae Son Eenjun Hwang |
| author_sort | Jihoon Moon |
| collection | DOAJ |
| description | A stable power supply is very important in the management of power infrastructure. One of the critical tasks in accomplishing this is to predict power consumption accurately, which usually requires considering diverse factors, including environmental, social, and spatial-temporal factors. Depending on the prediction scope, building type can also be an important factor since the same types of buildings show similar power consumption patterns. A university campus usually consists of several building types, including a laboratory, administrative office, lecture room, and dormitory. Depending on the temporal and external conditions, they tend to show a wide variation in the electrical load pattern. This paper proposes a hybrid short-term load forecast model for an educational building complex by using random forest and multilayer perceptron. To construct this model, we collect electrical load data of six years from a university campus and split them into training, validation, and test sets. For the training set, we classify the data using a decision tree with input parameters including date, day of the week, holiday, and academic year. In addition, we consider various configurations for random forest and multilayer perceptron and evaluate their prediction performance using the validation set to determine the optimal configuration. Then, we construct a hybrid short-term load forecast model by combining the two models and predict the daily electrical load for the test set. Through various experiments, we show that our hybrid forecast model performs better than other popular single forecast models. |
| first_indexed | 2024-04-12T19:41:48Z |
| format | Article |
| id | doaj.art-2ae8873e6844492cac03b8b42d1ca329 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-12T19:41:48Z |
| publishDate | 2018-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-2ae8873e6844492cac03b8b42d1ca3292022-12-22T03:19:04ZengMDPI AGEnergies1996-10732018-11-011112328310.3390/en11123283en11123283Hybrid Short-Term Load Forecasting Scheme Using Random Forest and Multilayer PerceptronJihoon Moon0Yongsung Kim1Minjae Son2Eenjun Hwang3School of Electrical Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, KoreaSoftware Policy & Research Institute (SPRi), 22, Daewangpangyo-ro 712 beon-gil, Bundang-gu, Seongnam-si, Gyeonggi-do 13488, KoreaSchool of Electrical Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, KoreaSchool of Electrical Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, KoreaA stable power supply is very important in the management of power infrastructure. One of the critical tasks in accomplishing this is to predict power consumption accurately, which usually requires considering diverse factors, including environmental, social, and spatial-temporal factors. Depending on the prediction scope, building type can also be an important factor since the same types of buildings show similar power consumption patterns. A university campus usually consists of several building types, including a laboratory, administrative office, lecture room, and dormitory. Depending on the temporal and external conditions, they tend to show a wide variation in the electrical load pattern. This paper proposes a hybrid short-term load forecast model for an educational building complex by using random forest and multilayer perceptron. To construct this model, we collect electrical load data of six years from a university campus and split them into training, validation, and test sets. For the training set, we classify the data using a decision tree with input parameters including date, day of the week, holiday, and academic year. In addition, we consider various configurations for random forest and multilayer perceptron and evaluate their prediction performance using the validation set to determine the optimal configuration. Then, we construct a hybrid short-term load forecast model by combining the two models and predict the daily electrical load for the test set. Through various experiments, we show that our hybrid forecast model performs better than other popular single forecast models.https://www.mdpi.com/1996-1073/11/12/3283hybrid forecast modelelectrical load forecastingtime series analysisrandom forestmultilayer perceptron |
| spellingShingle | Jihoon Moon Yongsung Kim Minjae Son Eenjun Hwang Hybrid Short-Term Load Forecasting Scheme Using Random Forest and Multilayer Perceptron Energies hybrid forecast model electrical load forecasting time series analysis random forest multilayer perceptron |
| title | Hybrid Short-Term Load Forecasting Scheme Using Random Forest and Multilayer Perceptron |
| title_full | Hybrid Short-Term Load Forecasting Scheme Using Random Forest and Multilayer Perceptron |
| title_fullStr | Hybrid Short-Term Load Forecasting Scheme Using Random Forest and Multilayer Perceptron |
| title_full_unstemmed | Hybrid Short-Term Load Forecasting Scheme Using Random Forest and Multilayer Perceptron |
| title_short | Hybrid Short-Term Load Forecasting Scheme Using Random Forest and Multilayer Perceptron |
| title_sort | hybrid short term load forecasting scheme using random forest and multilayer perceptron |
| topic | hybrid forecast model electrical load forecasting time series analysis random forest multilayer perceptron |
| url | https://www.mdpi.com/1996-1073/11/12/3283 |
| work_keys_str_mv | AT jihoonmoon hybridshorttermloadforecastingschemeusingrandomforestandmultilayerperceptron AT yongsungkim hybridshorttermloadforecastingschemeusingrandomforestandmultilayerperceptron AT minjaeson hybridshorttermloadforecastingschemeusingrandomforestandmultilayerperceptron AT eenjunhwang hybridshorttermloadforecastingschemeusingrandomforestandmultilayerperceptron |