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

Abstract

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).

Implications of war on the food, beverage, and tobacco industry in South Korea

“…There are many statistical models available that we can use to predict the stock price movement using historical stock prices. However, with the development of machine learning algorithms, prediction models gradually shifted from traditional statistical models to deep learning models (Benvenuto et al, 2020 ; Michalková and Pobočíková, 2023 ; Nand et al, 2023 ). The purpose of using the ARIMA model for forecasting future returns is that the historical values of the stock returns can predict future stock returns.…”

Gas data anomaly detection based on time-series ARIMA model

“…The currently used ARIMA time series are specified according to the actual situation [16] : autoregressive model (AR), moving average model (MA), autoregressive-moving average model (ARMA) and differentially integrated moving average autoregressive model (ARIMA).…”

“…The test results in Figure 2(a) correspond to normal data, and the detection results in Figure 2(b), (c), and (d) correspond to static anomalies, mutational anomalies, and periodic anomalies, respectively [15][16][17] . In Figure 2, the solid pink line indicates the data to be detected, i.e., the data of the test set, the dashed blue line indicates the predicted data of the model, and the red line outside the pink area indicates the types of anomalies marked in Figure 2.…”

Evolution of Green Energy Production in Czech Republic

“…A simple scheme of a neural network is shown in Figure 5, based on [29]. The model for Czech Republic renewable energy generation was prepared according to [29,34]. The model was trained on historical energy consumption data from [20,25].…”