Short-Term Energy Consumption Forecasting Analysis Using Different Optimization and Activation Functions with Deep Learning Models

Modelling events that change over time is one of the most difficult problems in data analysis. Forecasting of time-varying electric power values is also an important problem in data analysis. Regression methods, machine learning, and deep learning methods are used to learn different patterns from da...

Full description

Saved in:
Bibliographic Details
Main Authors: Mehmet Tahir Ucar, Asim Kaygusuz
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/12/6839
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849467411435094016
author Mehmet Tahir Ucar
Asim Kaygusuz
author_facet Mehmet Tahir Ucar
Asim Kaygusuz
author_sort Mehmet Tahir Ucar
collection DOAJ
description Modelling events that change over time is one of the most difficult problems in data analysis. Forecasting of time-varying electric power values is also an important problem in data analysis. Regression methods, machine learning, and deep learning methods are used to learn different patterns from data and develop a consumption prediction model. The aim of this study is to determine the most successful models for short-term power consumption prediction with deep learning and to achieve the highest prediction accuracy. In this study, firstly, the data was evaluated and organized with exploratory data analysis (EDA) on a ready dataset and the features of the data were extracted. Studies were carried out on long short-term memory (LSTM), gated recurrent unit (GRU), simple recurrent neural networks (SimpleRNN) and bidirectional long short-term memory (BiLSTM) architectures. First, four architectures were used with 11 different optimization methods. In this study, it was seen that a high success rate of 0.9972 was achieved according to the R<sup>2</sup> score index. In the following, the first study was tried with different epoch numbers. Afterwards, this study was carried out with 264 separate models produced using four architectures, 11 optimization methods, and six activation functions in order. The results of all these studies were obtained according to the root mean square error (RMSE), mean absolute error (MAE), and R<sup>2</sup>_score indexes. The R<sup>2</sup>_score indexes graphs are presented. Finally, the 10 most successful applications are listed.
format Article
id doaj-art-fac3f5a3e5304563808df6ff2a7ae732
institution Kabale University
issn 2076-3417
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-fac3f5a3e5304563808df6ff2a7ae7322025-08-20T03:26:15ZengMDPI AGApplied Sciences2076-34172025-06-011512683910.3390/app15126839Short-Term Energy Consumption Forecasting Analysis Using Different Optimization and Activation Functions with Deep Learning ModelsMehmet Tahir Ucar0Asim Kaygusuz1Ergani Vocational School, Dicle University, 21280 Diyarbakır, TürkiyeDepartment of Electrical and Electronics Engineering, Engineering Faculty, Inonu University, 44280 Malatya, TürkiyeModelling events that change over time is one of the most difficult problems in data analysis. Forecasting of time-varying electric power values is also an important problem in data analysis. Regression methods, machine learning, and deep learning methods are used to learn different patterns from data and develop a consumption prediction model. The aim of this study is to determine the most successful models for short-term power consumption prediction with deep learning and to achieve the highest prediction accuracy. In this study, firstly, the data was evaluated and organized with exploratory data analysis (EDA) on a ready dataset and the features of the data were extracted. Studies were carried out on long short-term memory (LSTM), gated recurrent unit (GRU), simple recurrent neural networks (SimpleRNN) and bidirectional long short-term memory (BiLSTM) architectures. First, four architectures were used with 11 different optimization methods. In this study, it was seen that a high success rate of 0.9972 was achieved according to the R<sup>2</sup> score index. In the following, the first study was tried with different epoch numbers. Afterwards, this study was carried out with 264 separate models produced using four architectures, 11 optimization methods, and six activation functions in order. The results of all these studies were obtained according to the root mean square error (RMSE), mean absolute error (MAE), and R<sup>2</sup>_score indexes. The R<sup>2</sup>_score indexes graphs are presented. Finally, the 10 most successful applications are listed.https://www.mdpi.com/2076-3417/15/12/6839deep learning modelselectricity consumption predictionexploratory data analysis (EDA)long short-term memory (LSTM)gated recurrent unit (GRU)simple recurrent neural networks (Simple RNN)
spellingShingle Mehmet Tahir Ucar
Asim Kaygusuz
Short-Term Energy Consumption Forecasting Analysis Using Different Optimization and Activation Functions with Deep Learning Models
Applied Sciences
deep learning models
electricity consumption prediction
exploratory data analysis (EDA)
long short-term memory (LSTM)
gated recurrent unit (GRU)
simple recurrent neural networks (Simple RNN)
title Short-Term Energy Consumption Forecasting Analysis Using Different Optimization and Activation Functions with Deep Learning Models
title_full Short-Term Energy Consumption Forecasting Analysis Using Different Optimization and Activation Functions with Deep Learning Models
title_fullStr Short-Term Energy Consumption Forecasting Analysis Using Different Optimization and Activation Functions with Deep Learning Models
title_full_unstemmed Short-Term Energy Consumption Forecasting Analysis Using Different Optimization and Activation Functions with Deep Learning Models
title_short Short-Term Energy Consumption Forecasting Analysis Using Different Optimization and Activation Functions with Deep Learning Models
title_sort short term energy consumption forecasting analysis using different optimization and activation functions with deep learning models
topic deep learning models
electricity consumption prediction
exploratory data analysis (EDA)
long short-term memory (LSTM)
gated recurrent unit (GRU)
simple recurrent neural networks (Simple RNN)
url https://www.mdpi.com/2076-3417/15/12/6839
work_keys_str_mv AT mehmettahirucar shorttermenergyconsumptionforecastinganalysisusingdifferentoptimizationandactivationfunctionswithdeeplearningmodels
AT asimkaygusuz shorttermenergyconsumptionforecastinganalysisusingdifferentoptimizationandactivationfunctionswithdeeplearningmodels