Abstract: discipline about computer architecture has long researched electricity consumption in great detail. While energy acquisition as a machine learning metric is starting to gain traction, majority about experiments are still primarily focused on achieving extremely high levels about accuracy among no computational constraints. We think that one about reasons for this lack about interest is because people don't easily have access to information on energy consumption. major goal about this research is to evaluate helpful regulations for machine learning community, enabling them to use & develop energy estimation techniques for machine learning algorithms. LSTM, linear regression, random forest regression, & other ensemble models are used to forecast electricity & produce precise results. We also provide two use cases that support investigation about energy exhaustion in machine learning, as well as most recent software tools that provide electricity estimating methods. through using updated smart metres that allow everyone to see who is consuming more energy in what appliances, we are able to accurately estimate future energy that will be very useful to grid in determining when we will need more & less energy.

Keywords: Machine Learning, Lstm.

PDF | DOI: 10.17148/IJARCCE.2022.111136

Open chat
Chat with IJARCCE