GUI Energy Demand Forecast using LSTM Deep Learning Model in Python Platform

B, Rohith; Santhosh, T. V.; Alfred, Romain; Singh, Rahul Kumar

doi:10.1109/i-pact52855.2021.9696760

Cited by 1 publication

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In most of the situations, the electricity generated from renewable energy sources imported to national grids are intermittent which need to be managed with the distribution of renewable energy for the local energy demanding [1] [4]. Smart grid systems can collect data for the management of national grids and for the improvement of the services [4] [5].…”

Section: Introductionmentioning

confidence: 99%

“…There recently have been a body of studies on forecasting power consumption, including the use of LSTM to forecast energy consumption for short term and its comparison with support vector machine and rainforest algorithm [6]. Another research created a model via combining GUI (Graphic User Interface) and LSTM, and compared the LSTM performance to the real readings [4]. Many other papers have used statistical methods to estimate the coefficient of variables, such as regression, multiple linear regressions (MLR), and autoregressive integrated moving average (ARIMA) [7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Electricity Demand Forecast with LSTMs

Ossman,

2024

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Long-Short Term Memory (LSTM) networks are able to learn the complicated relationships between variables from previous and current timesteps over time series data and use them to do specific forecast tasks. LSTMs are basically stacks of perceptron algorithms, the more stacks a neural network has, the deeper the neural network. There are two types of gradient propagations over LSTM networks -forward and backward. However there is a common vanishing issue when developing LSTM networks. This paper proposes two LSTM models developed with sequence-to-sequence and sequence-to-vector frames and investigates possible empirical solutions to the vanishing issue, particularly, in the context of predicting multivariate and univariate power demands through comparative evaluation on electricity demand data.

show abstract

Section: Introductionmentioning

confidence: 99%