Forecasting of Turkey’s Electrical Energy Consumption using LSTM and GRU Networks

Bişkin, Osman Tayfun; Çifci, Ahmet

doi:10.35193/bseufbd.935824

Cited by 5 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The electricity demand of Türkiye for the 2009-2018 period is considered in another study in which the artificial neural networks and the multivariate regression analysis are used where the population, average household size, GDP, imports, export s and the education level are the inputs (Ulku and Yalpir, 2021). In another work, the hourly electricity demand forecasting of Türkiye is performed employing the long short-term memory (LSTM) and the gated recurrent unit (GRU) models (Biskin and Cifci, 2021). The artificial neural networks is used in another study for the modelling of the electricity consumption of TR81 region (Zonguldak, Karabuk and Bartin provinces of Türkiye) where the population, import, export and the building areas data are taken as inputs and forecasts are performed for the 2016-2020 period (Kocadayi et al, 2017).…”

Section: Literature Analysismentioning

confidence: 99%

Estimation of the Electricity Supply and Demand of Türkiye Employing Deep Learning Networks

Tuncsiper¹

2023

IJMRA

View full text Add to dashboard Cite

Electrical energy, one of the indispensable elements of the economic and social life, is an energy source that has to be provided without interruption in order to ensure the continuity of development. In this work, the monthly electricity supply and demand of Türkiye for the period of 2016-2022 are modelled using advanced machine learning techniques. An autoregressive deep learning network consisting of four hidden layers is developed for the modelling of the electricity supply and demand da ta having the form of multilayer perceptron artificial neural network. The electricity supply and demand data of Türkiye is gathered from the official sources and then investigated utilizing the seasonality analysis. Then, the deep learning network is developed in Python programming language. The 70% of the available electricity supply and demand data are used as the training data whereas the remaining 30% of the data is the test data. The randomized selection of the train and test data are performed using the classes available in the SciKit-Learn library of the Python programming language. The performance of the developed deep learning network model is evaluated both by plotting the actual and the modelled data on the same axis pair and by using performance metrics of the coefficient of determination, mean absolute error, mean absolute percentage error and the root mean square error. The mean absolute percentage errors of the models have the values of 2.29% and 2.17% for the electricity supply and demand data, respectively, indicating the success of the developed deep learning model for the modelling and the estimation of the electricity supply and demand data. The developed model is considered to be useful for the economic and technical energy planners.

show abstract

Section: Literature Analysismentioning

confidence: 99%

Estimation of the Electricity Supply and Demand of Türkiye Employing Deep Learning Networks

Tuncsiper¹

2023

IJMRA

View full text Add to dashboard Cite

show abstract

“…The GRU is a gate unit that modulates the flow of information within the unit without a separate memory cell [18]. GRU is a method of Recurrent Neural Network (RNN) [19]. GRU has a more straightforward underlying structure than LSTM, making it easier to train and requiring fewer computations [20].…”

Section: Gated Recurrent Unitmentioning

confidence: 99%

Time Series Forecasting of Significant Wave Height using GRU, CNN-GRU, and LSTM

Alfredo

Adytia

2022

J. RESTI (Rekayasa Sist. Teknol. Inf.)

View full text Add to dashboard Cite

Predicting wave height is essential to reduce significant risks for shipping or activities carried out at sea. Waves inherit a stochastic nature, mainly generated by wind and propagated through the ocean, making them challenging to forecast. In this paper, we design time series wave forecasting using a deep learning model, which is a hybrid Convolutional Neural Network (CNN)-Gated Recurrent Unit (GRU) or CNN-GRU. We use two time series of wave data sets, i.e., reanalysis data from ERA5 by ECMWF and GFS from NOAA. As a study area, we choose Pelabuhan Ratu, located in the south of West Java which is connected to the open Indian Ocean. Moreover, we also compare the results by using other deep learning models, i.e., the Long Short-Term Memory (LSTM) and GRU. We evaluated these models to forecast 7, 14, and 30 days. Models' performance is assessed using RMSE, MAPE, and Correlation Coefficient (CC). For predicting 30 days, using the ERA5 data, the CNN-GRU model produces relatively accurate results with an RMSE value of 1.8844 and CC of 0.9938, whereas for the GFS data, results in RMSE value of 1.8852 and CC of 0.9915.

show abstract

A Deep Learning-Based Demand Forecasting System for Planning Electricity Generation

Gökçe,

Duman

2024

Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi

View full text Add to dashboard Cite

In today's world, where economic and industrial development continues, the importance of electrical energy is constantly increasing. Energy demand should be forecast as precisely as possible to reduce lost energy costs in the system, to plan generation expenditures appropriately, to ensure that market players are not economically harmed, and to deliver quality and uninterrupted energy to system consumers. Balancing the electric energy supply and demand of the system is possible with a forecasting plan. Our research aims to generate hourly electricity consumption load forecasts for the period 2018-2021 using Turkish Electricity Consumption Data and meteorological data, with the addition of time and public holiday features. The forecasting performance of the models is evaluated by training multiple machine learning models and deep neural network-based time series models with the data. When the prediction results of our load demand forecasting problem were evaluated, it was seen that deep learning methods gave higher results in prediction success compared to machine learning models. It has been observed that the prediction success of the LSTM model, one of the deep learning methods we use, is higher than the RNN and GRU models. The analysis envisages the elimination of mismatches between energy supply and demand.

show abstract

Forecasting of Turkey’s Electrical Energy Consumption using LSTM and GRU Networks

Cited by 5 publications

References 33 publications

Estimation of the Electricity Supply and Demand of Türkiye Employing Deep Learning Networks

Estimation of the Electricity Supply and Demand of Türkiye Employing Deep Learning Networks

Time Series Forecasting of Significant Wave Height using GRU, CNN-GRU, and LSTM

A Deep Learning-Based Demand Forecasting System for Planning Electricity Generation

Contact Info

Product

Resources

About