Spatiotemporal Sequence-to-Sequence Clustering for Electric Load Forecasting
Massive electrical load exhibits many patterns making it difficult for forecast algorithms to generalise well. Most learning algorithms produce a better forecast for dominant patterns in the case of weekday consumption and otherwise for less dominant patterns in weekend and holiday consumption. In v...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10013668/ |
| _version_ | 1797902212557438976 |
|---|---|
| author | Moses Amoasi Acquah Yuwei Jin Byeong-Chan Oh Yeong-Geon Son Sung-Yul Kim |
| author_facet | Moses Amoasi Acquah Yuwei Jin Byeong-Chan Oh Yeong-Geon Son Sung-Yul Kim |
| author_sort | Moses Amoasi Acquah |
| collection | DOAJ |
| description | Massive electrical load exhibits many patterns making it difficult for forecast algorithms to generalise well. Most learning algorithms produce a better forecast for dominant patterns in the case of weekday consumption and otherwise for less dominant patterns in weekend and holiday consumption. In view of this, there is the need to cluster the load patterns, so learning algorithms can focus on the patterns independently to produce forecasts with better accuracy for all cases. However, clustering time-series data breaks the time-series dependency, making model training difficult. This paper presents a novel sequence-to-sequence cluster framework to reform time-series dependency after clustering; this enables independent clusters to be modelled using Convolutional Neural Network-Gated Recurrent Unit, which learns spatiotemporal features for future forecasts. A real-world dataset by the Korea Power Exchange composed of nationwide consumption is used for case studies and experiments. Experimental results verify that the proposed study effectively improves the accuracy of electric load forecasting by about 50%, with a WAPE of 0.67%. The proposed method also speeds up the training process of the forecast algorithm by about 35%, given that only a subset of the dataset is trained due to clustering. Korea Water Resources Corporation has implemented the proposed method for load forecasting and system marginal price estimation. |
| first_indexed | 2024-04-10T09:14:08Z |
| format | Article |
| id | doaj.art-47a76c930d8542a8b24d57299ad9043a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-10T09:14:08Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-47a76c930d8542a8b24d57299ad9043a2023-02-21T00:01:57ZengIEEEIEEE Access2169-35362023-01-01115850586310.1109/ACCESS.2023.323572410013668Spatiotemporal Sequence-to-Sequence Clustering for Electric Load ForecastingMoses Amoasi Acquah0https://orcid.org/0000-0002-2669-5029Yuwei Jin1https://orcid.org/0000-0001-8025-8404Byeong-Chan Oh2Yeong-Geon Son3https://orcid.org/0000-0002-7849-2848Sung-Yul Kim4https://orcid.org/0000-0003-3530-9748Department of Electrical Energy Engineering, Keimyung University, Daegu, South KoreaDepartment of Electrical and Electronic Engineering, Kyungpook National University, Daegu, South KoreaDepartment of Electrical Energy Engineering, Keimyung University, Daegu, South KoreaDepartment of Electrical Energy Engineering, Keimyung University, Daegu, South KoreaDepartment of Electrical Energy Engineering, Keimyung University, Daegu, South KoreaMassive electrical load exhibits many patterns making it difficult for forecast algorithms to generalise well. Most learning algorithms produce a better forecast for dominant patterns in the case of weekday consumption and otherwise for less dominant patterns in weekend and holiday consumption. In view of this, there is the need to cluster the load patterns, so learning algorithms can focus on the patterns independently to produce forecasts with better accuracy for all cases. However, clustering time-series data breaks the time-series dependency, making model training difficult. This paper presents a novel sequence-to-sequence cluster framework to reform time-series dependency after clustering; this enables independent clusters to be modelled using Convolutional Neural Network-Gated Recurrent Unit, which learns spatiotemporal features for future forecasts. A real-world dataset by the Korea Power Exchange composed of nationwide consumption is used for case studies and experiments. Experimental results verify that the proposed study effectively improves the accuracy of electric load forecasting by about 50%, with a WAPE of 0.67%. The proposed method also speeds up the training process of the forecast algorithm by about 35%, given that only a subset of the dataset is trained due to clustering. Korea Water Resources Corporation has implemented the proposed method for load forecasting and system marginal price estimation.https://ieeexplore.ieee.org/document/10013668/Convolutional neural network-gated recurrent unit (CNN-GRU)feature engineeringk-means clusteringLightGBM classifiersequence-to-sequence forecastshort-term load forecast (STLF) |
| spellingShingle | Moses Amoasi Acquah Yuwei Jin Byeong-Chan Oh Yeong-Geon Son Sung-Yul Kim Spatiotemporal Sequence-to-Sequence Clustering for Electric Load Forecasting IEEE Access Convolutional neural network-gated recurrent unit (CNN-GRU) feature engineering k-means clustering LightGBM classifier sequence-to-sequence forecast short-term load forecast (STLF) |
| title | Spatiotemporal Sequence-to-Sequence Clustering for Electric Load Forecasting |
| title_full | Spatiotemporal Sequence-to-Sequence Clustering for Electric Load Forecasting |
| title_fullStr | Spatiotemporal Sequence-to-Sequence Clustering for Electric Load Forecasting |
| title_full_unstemmed | Spatiotemporal Sequence-to-Sequence Clustering for Electric Load Forecasting |
| title_short | Spatiotemporal Sequence-to-Sequence Clustering for Electric Load Forecasting |
| title_sort | spatiotemporal sequence to sequence clustering for electric load forecasting |
| topic | Convolutional neural network-gated recurrent unit (CNN-GRU) feature engineering k-means clustering LightGBM classifier sequence-to-sequence forecast short-term load forecast (STLF) |
| url | https://ieeexplore.ieee.org/document/10013668/ |
| work_keys_str_mv | AT mosesamoasiacquah spatiotemporalsequencetosequenceclusteringforelectricloadforecasting AT yuweijin spatiotemporalsequencetosequenceclusteringforelectricloadforecasting AT byeongchanoh spatiotemporalsequencetosequenceclusteringforelectricloadforecasting AT yeonggeonson spatiotemporalsequencetosequenceclusteringforelectricloadforecasting AT sungyulkim spatiotemporalsequencetosequenceclusteringforelectricloadforecasting |