| Title |
Machine learning approach for power consumption model based on monsoon data for smart cities applications |
| ID_Doc |
39599 |
| Authors |
Shah, SSM; Meganathan, S |
| Title |
Machine learning approach for power consumption model based on monsoon data for smart cities applications |
| Year |
2021 |
| Published |
Computational Intelligence, 37, 3 |
| DOI |
10.1111/coin.12368 |
| Abstract |
In this modern world, electricity plays a vital role. It is essential for human life and also affects normal behavior of environment resulting in global warming. Recent developments in artificial intelligence (AI), in particular machine learning (ML), have been significantly advancing smart city applications. Smart infrastructure, which is an essential component of smart cities, is equipped with power systems designed for optimizing smart devices. In this article, real domestic consumption data of 500 consumers from TANGEDCO are analyzed and clustered based on different seasons (consumption rate varies upon different weather conditions) for smart city applications. An efficient clustering algorithm k-means integrates big data set for a period of 10 years and converts it into clustering graph with three seasons. By analyzing this data, the amount of consumption of electricity by humans in particular area (Pasupathikovil) of Papanasam taluk of Thanjavur district will be predicted. This article would be more useful for predicting changes in usage of electricity and take proper steps for analyzing the consumption accordingly and it will be more useful in smart city development. It gives an idea of which season needs more consumption and which needs less. |
| Author Keywords |
clustering; K-means; machine learning methods; smart city; TANGEDCO |
| Index Keywords |
Index Keywords |
| Document Type |
Other |
| Open Access |
Open Access |
| Source |
Science Citation Index Expanded (SCI-EXPANDED) |
| EID |
WOS:000546496500001 |
| WoS Category |
Computer Science, Artificial Intelligence |
| Research Area |
Computer Science |
| PDF |
|