Implementing the Optimum LSTM Optimizer for Power Consumption

Implementing the Optimum LSTM Optimizer for Power Consumption

Dr Kanmani P¹, Anjali.S², Sakchi Choudhary³

Department of Data Science and Business Systems, SRM Institute of Science and Technology, Chennai, India

Department of Data Science and Business Systems, SRM Institute of Science and Technology, Chennai, India

Department of Data Science and Business Systems, SRM Institute of Science and Technology, Chennai, India

---------------------------------------------------------------------***---------------------------------------------------------------------

Abstract - Electricity is an essential component that can't be overlooked in any home anywhere in the world. It is one of the most important attributes that determine a person's overall standard of living. When we look at the quantity of energy consumed in a certain household, one of the most significant factors to take into consideration is the amount of power consumed. The term "power consumption" refers to the amount of electrical energy that is used during a particular period of time. The department for power supply can better comprehend the power consumption of residents and also predict whether or not there will be any anomalous power consuming phenomena by analyzing the power consumption of any individual household.

The utilization of energy in homes is responsible for roughly one third of the total demand for primary energy on a global scale and has a substantial impact on the environment. The purpose of this article is to determine which optimizer produces the most accurate results when estimating the amount of electricity that will be used over the next 12 days by building an LSTM model. LSTM is one of the deep learning models that is utilized most frequently. It is also one of the best models to employ for projecting events that will occur in the near future.

Key Words:  power consumption, LSTM, Adam, Adadelta, SGD, RMSprop