Analysis of classical and machine learning based short-term and mid-term load forecasting for smart grid
The evolution of advanced metering infrastructure (AMI) has increased the electricity consumption data in real-time manifolds. Using this massive data, the load forecasting methods have undergone numerous transformations. In this paper, short-term and mid-term load forecasting (STLF and MTLF) is pro...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2021-10-01
|
Series: | International Journal of Sustainable Energy |
Subjects: | |
Online Access: | http://dx.doi.org/10.1080/14786451.2021.1873339 |
_version_ | 1797680286690967552 |
---|---|
author | Sneha Rai Mala De |
author_facet | Sneha Rai Mala De |
author_sort | Sneha Rai |
collection | DOAJ |
description | The evolution of advanced metering infrastructure (AMI) has increased the electricity consumption data in real-time manifolds. Using this massive data, the load forecasting methods have undergone numerous transformations. In this paper, short-term and mid-term load forecasting (STLF and MTLF) is proposed using smart-metered data acquired from a real-life distribution grid at the NIT Patna campus with different classical and machine learning methods. Data pre-processing is done to transform the raw data into an appropriate format by removing the outliers present in the datasets. The influential meteorological variables obtained by correlation analysis along with the past load are used to train the load forecasting model. The proposed support vector regression (SVR) produces the best forecasting performance for the test system with a minimum mean absolute percentage error (MAPE) and root mean square error (RMSE). The proposed method outperforms the existing approaches for STLF and MTLF by an average MAPE of 3.60. |
first_indexed | 2024-03-11T23:28:18Z |
format | Article |
id | doaj.art-e1fb1f25cf1f46b199fd6ddab77d23ba |
institution | Directory Open Access Journal |
issn | 1478-6451 1478-646X |
language | English |
last_indexed | 2024-03-11T23:28:18Z |
publishDate | 2021-10-01 |
publisher | Taylor & Francis Group |
record_format | Article |
series | International Journal of Sustainable Energy |
spelling | doaj.art-e1fb1f25cf1f46b199fd6ddab77d23ba2023-09-20T10:33:47ZengTaylor & Francis GroupInternational Journal of Sustainable Energy1478-64511478-646X2021-10-0140982183910.1080/14786451.2021.18733391873339Analysis of classical and machine learning based short-term and mid-term load forecasting for smart gridSneha Rai0Mala De1National Institute of Technology PatnaNational Institute of Technology PatnaThe evolution of advanced metering infrastructure (AMI) has increased the electricity consumption data in real-time manifolds. Using this massive data, the load forecasting methods have undergone numerous transformations. In this paper, short-term and mid-term load forecasting (STLF and MTLF) is proposed using smart-metered data acquired from a real-life distribution grid at the NIT Patna campus with different classical and machine learning methods. Data pre-processing is done to transform the raw data into an appropriate format by removing the outliers present in the datasets. The influential meteorological variables obtained by correlation analysis along with the past load are used to train the load forecasting model. The proposed support vector regression (SVR) produces the best forecasting performance for the test system with a minimum mean absolute percentage error (MAPE) and root mean square error (RMSE). The proposed method outperforms the existing approaches for STLF and MTLF by an average MAPE of 3.60.http://dx.doi.org/10.1080/14786451.2021.1873339smart meteringshort-term and mid-term load forecastingmlrannoptimised holt’s methodsvr |
spellingShingle | Sneha Rai Mala De Analysis of classical and machine learning based short-term and mid-term load forecasting for smart grid International Journal of Sustainable Energy smart metering short-term and mid-term load forecasting mlr ann optimised holt’s method svr |
title | Analysis of classical and machine learning based short-term and mid-term load forecasting for smart grid |
title_full | Analysis of classical and machine learning based short-term and mid-term load forecasting for smart grid |
title_fullStr | Analysis of classical and machine learning based short-term and mid-term load forecasting for smart grid |
title_full_unstemmed | Analysis of classical and machine learning based short-term and mid-term load forecasting for smart grid |
title_short | Analysis of classical and machine learning based short-term and mid-term load forecasting for smart grid |
title_sort | analysis of classical and machine learning based short term and mid term load forecasting for smart grid |
topic | smart metering short-term and mid-term load forecasting mlr ann optimised holt’s method svr |
url | http://dx.doi.org/10.1080/14786451.2021.1873339 |
work_keys_str_mv | AT sneharai analysisofclassicalandmachinelearningbasedshorttermandmidtermloadforecastingforsmartgrid AT malade analysisofclassicalandmachinelearningbasedshorttermandmidtermloadforecastingforsmartgrid |