Forecasting of Electrical Energy Consumption in Slovakia

Pavličko, Michal; Vojtekova, Maria; Blažeková, Oľga

doi:10.3390/math10040577

Cited by 26 publications

(6 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dumitru and Gligor have studied wind power forecasting in South European countries with ANN [28]. Pavlicko et al have studied forecasting models to predict Slovakia's maximum hourly electricity consumption per day with ANN and used different models, like the transverse set of Grey models, nonlinear Grey Bernoulli models, multi-layer feedforward back-propagation networks, and hybrid models combining these [29].…”

Section: Introductionmentioning

confidence: 99%

Forecasting of G7 Countries' Total Energy Production: A Rigorous Exploration with Artificial Neural Networks and Multiple Linear Regression

BAYIR,

KILIÇ,

DİRİ

et al. 2024

Preprint

View full text Add to dashboard Cite

The G7 countries, consisting of Canada, France, Germany, Italy, Japan, the United Kingdom, and the United States, have important collaborations in energy production to achieve energy security. One of the main systems of Artificial intelligence's, artificial neural networks (ANN), is crucial to this area of study, comparatively using Multiple Linear Regression (MLR) comparatively. ANN and MLR are feasible to use across the G7 countries' total energy production numbers, and these numbers were determined using ANN and MLR forecasting techniques. The data included the years 1990–2020, focusing on GDP intensity, refined oil product production, electricity production, and renewable energy proportion. In ANN modeling, the best regression results at 10*10 have been obtained with two hidden layers. All regression values were 0.99947, with the training regression value being 0.99912, the validation regression value being 0.99997, and the test regression value being 0.99997. The results showed high accuracy, with regression scores exceeding 99% and smaller prediction error values. A paired sample t test has been applied to see whether the distinction between the average values is significant or not. The results of the test between the actual and predicted values (p = 0.7462 > 0.05) revealed that the forecasted values have been quite close to the actual values. Total energy production Mean Absolute Deviation (MAD), Mean Squared Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) parameters have been calculated as 4.364, 34.072, 5.837, and 0.162, respectively. The research proved that ANNs are effective in forecasting total energy output. And, with MLR, error values for MAD, MSE, RMSE, and MAPE were also found to be 5.364, 34.352, 5.861, and 1.609, respectively, using MLR modeling. By 2035, the G7 nations are expected to produce 50,652.746 Mtoe of energy collectively. The research proved that ANNs are effective in forecasting total energy output.

show abstract

Section: Introductionmentioning

confidence: 99%

Forecasting of G7 Countries' Total Energy Production: A Rigorous Exploration with Artificial Neural Networks and Multiple Linear Regression

BAYIR,

KILIÇ,

DİRİ

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The number of papers providing the prediction models regarding the energy sector in Slovakia is scarce. Recently, Pavlicko et al [15] forecast the electricity consumption in Slovakia by applying and comparing two approaches -grey models and multi-layer feed-forward back-propagation network. They also proposed a new model combining both approaches.…”

Section: Introductionmentioning

confidence: 99%

Time Series Analysis of Fossil Fuels Consumption in Slovakia by Arima Model

Michalková

Pobocikova

2023

Acta Mechanica Et Automatica

View full text Add to dashboard Cite

According to the Green Deal, the carbon neutrality of the European Union (EU) should be reached partly by the transition from fossil fuels to alternative renewable sources. However, fossil fuels still play an essential role in energy production, and are widely used in the world with no alternative to be completely replaced with, so far. In recent years, we have observed the rapidly growing prices of commodities such as oil or gas. The analysis of past fossil fuels consumption might contribute significantly to the responsible formulation of the energy policy of each country, reflected in policies of related organisations and the industrial sector. Over the years, a number of papers have been published on modelling production and consumption of fossil and renewable energy sources on the level of national economics, industrial sectors and households, exploiting and comparing a variety of approaches. In this paper, we model the consumption of fossil fuels (gas and coal) in Slovakia based on the annual data during the years 1965–2020. To our knowledge, no such model, which analyses historical data and provides forecasts for future consumption of gas and coal, respectively, in Slovakia, is currently available in the literature. For building the model, we have used the Box–Jenkins methodology. Because of the presence of trend in the data, we have considered the autoregressive integrated moving average (ARIMA (p,d,q)) model. By fitting models with various combinations of parameters p, d, q, the best fitting model has been chosen based on the value of Akaike’s information criterion. According to this, the model for coal consumption is ARIMA(0, 2, 1) and for gas consumption it is ARIMA(2, 2, 2).

show abstract

“…In Slovakia, Pavlicko et al proposed models for forecasting the daily maximum hourly electricity consumption that are more accurate than the official load forecasts of the Slovak distribution company [4]. In their publication, they present and compare different models.…”

Section: Introductionmentioning

confidence: 99%

Peak Electrical Energy Consumption Prediction by ARIMA, LSTM, GRU, ARIMA-LSTM and ARIMA-GRU Approaches

Pierre,

Akim,

Semenyo

et al. 2023

Energies

View full text Add to dashboard Cite

Forecasting peak electrical energy consumption is important because it allows utilities to properly plan for the production and distribution of electrical energy. This reduces operating costs and avoids power outages. In addition, it can help reduce environmental impact by allowing for more efficient power generation and reducing the need for additional fossil fuels during periods of high demand. In the current work, electric power consumption data from “Compagnie Electrique du Benin (CEB)” was used to deduce the peak electric power consumption at peak hours. The peak consumption of electric power was predicted using hybrid approaches based on traditional time series prediction methods (autoregressive integrated moving average (ARIMA)) and deep learning methods (long short-term memory (LSTM), gated recurrent unit (GRU)). The ARIMA approach was used to model the trend term, while deep learning approaches were employed to interpret the fluctuation term, and the outputs from these models were combined to provide the final result. The hybrid approach, ARIMA-LSTM, provided the best prediction performance with root mean square error (RMSE) of 7.35, while for the ARIMA-GRU hybrid approach, the RMSE was 9.60. Overall, the hybrid approaches outperformed the single approaches, such as GRU, LSTM, and ARIMA, which exhibited RMSE values of 18.11, 18.74, and 49.90, respectively.

show abstract

Forecasting of Electrical Energy Consumption in Slovakia

Cited by 26 publications

References 38 publications

Forecasting of G7 Countries' Total Energy Production: A Rigorous Exploration with Artificial Neural Networks and Multiple Linear Regression

Forecasting of G7 Countries' Total Energy Production: A Rigorous Exploration with Artificial Neural Networks and Multiple Linear Regression

Time Series Analysis of Fossil Fuels Consumption in Slovakia by Arima Model

Peak Electrical Energy Consumption Prediction by ARIMA, LSTM, GRU, ARIMA-LSTM and ARIMA-GRU Approaches

Contact Info

Product

Resources

About