
Research Article
Estimation of Power Consumption Prediction of Electricity Using Machine Learning
@INPROCEEDINGS{10.1007/978-3-031-48888-7_13, author={Paradhasaradhi Yeleswarpu and Rakesh Nayak and R. D. Patidar}, title={Estimation of Power Consumption Prediction of Electricity Using Machine Learning}, proceedings={Cognitive Computing and Cyber Physical Systems. 4th EAI International Conference, IC4S 2023, Bhimavaram, Andhra Pradesh, India, August 4-6, 2023, Proceedings, Part I}, proceedings_a={IC4S}, year={2024}, month={1}, keywords={Electricity consumption Random Forest AdaBoost Gridsearch CV Linear Regression Streamlit tool Machine Learning}, doi={10.1007/978-3-031-48888-7_13} }
- Paradhasaradhi Yeleswarpu
Rakesh Nayak
R. D. Patidar
Year: 2024
Estimation of Power Consumption Prediction of Electricity Using Machine Learning
IC4S
Springer
DOI: 10.1007/978-3-031-48888-7_13
Abstract
Electricity consumption has been broadly concentrated on in the PC engineering field since numerous years. While the securing of energy as an action in ML is arising, a large portion of the trial and error is still essentially centered around getting raised degrees of precision with no computational limitations. We accept that one of the reasons for this deficiency of interest is because of their shortfall of straightforwardness with admittance to assess energy utilization. The principal objective of this study is come to assess valuable guidelines to the MLpeople group that grants them the major acknowledgment to utilize and fabricate energy assessment techniques for AI calculations. Utilization of various group models like Linear Regression, and random forest regression and gride search cv, adaboost algorithms to predict the power and to acquire exact outcomes. Notwithstanding, we additionally present the state-of-the-art programming apparatuses that award power assessment standards, along with two use cases that reinforce the request of energy fatigue in ML. Toward the end, we anticipate the future energy which is so useful to the matrix to make exact energy for the network by refreshing with shrewd meters where everyone can know individuals, who are involving more energy in what machines, so it is gigantically useful in which time we want more energy and less energy.