Using Long Short-Term Memory Units for Time Series Forecasting
Dhyan Chandra Yadav, Laxman Sahoo, Sanjeev Kumar Mandal, G. Ravivarman, P. Vijayaraghavan, B. Vishwalinga Prasad · 2023
This paper specializes in using long short-time period memory (LSTM) networks for time collection forecasting. LSTM is a form of artificial recurrent neural network (RNN) that is especially properly-applicable to analyze from enjoy over long sequences of statistics. Not like conventional recurrent networks, LSTM networks can technique input sequences in each instruction, while also allowing for the protection of lengthy-time period dependencies and rapid convergence. It's far shown that these characteristics of LSTM networks allow them to be used efficaciously for forecasting time series consisting of inventory performance and electricity tendencies. Strategies inclusive of feeding the LSTM network data in a time step layout, the use of peephole connections, stacking a couple of layers and early stopping are discussed. Results are then presented and mentioned, demonstrating that LSTM networks can research complex lengthy-time period dependencies in time series facts and correctly forecast destiny values.