Energy Consumption and Price Forecasting Through Data-Driven Analysis Methods: A Review

Abstract

Prediction of energy consumption and price is crucial in formatting policies related to the global energy market, demand, and supply. Data-driven analysis methods are giving rise to innovations in the world energy sector, including energy finance and economics. This paper has critically evaluated expand writings committed to Energy finance and economics applications of data-driven analysis. This paper comes up with an extensive view of state of the art in the area, which is already discussed with a different procedure. This review recognizes the applications of data-driven analysis methods in various areas such as forecasting domestic, nationwide, and transport energy consumption and price forecasting of multiple commodities, including crude oil, natural gas, and electricity. We have investigated certain research papers and given conclusion based on their researched and proposed model's prediction results and accuracies in respective areas. Our study suggests that Artificial Neural Network (ANN), Support Vector Machine (SVM), and other proposed neural network models are the most effective methods among other statistical and machine learning methods.

Ergonomic system of forecasting and analysis of the probability of atmospheric air pollution by emissions of enterprises in the conditions of technogenic development of the world

“…The training set contains 183393 records, and the test set contains 20378 records (Figure 2). When analyzing the requirements for the system being developed, it was decided to use a feedforward neural network to predict AQI [6,11]. To perform this task, the Python language and the tensorflow.keras library were chosen to implement work with a neural network.…”

Digital twin with augmented state extended Kalman filters for forecasting electric power consumption of industrial production systems

“…Model-based approaches involve analytical and physical models, which require a large number of parameters that are often difficult to determine [ 7 ]. Data-driven methods are becoming popular due to progress in sensing technologies [ 8 ] and comprise statistical models, such as Non-Linear Regression and Multiple Linear Regression (MLR), and Machine Learning (ML) algorithms, such as Artificial Neural Network (ANN) and Support Vector Machine (SVM) [ 9 ].…”

Artificial Intelligence-Based Prediction of Spanish Energy Pricing and Its Impact on Electric Consumption

“…The ongoing conflict between Russia and Ukraine has highlighted the need for increased stability in the energy markets and the importance of ensuring a consistent and affordable energy supply. In this context, the use of AI models to predict energy pricing and electric consumption is particularly relevant [12,13]. The prediction of real-time prices has been previously proposed as a potential solution for enhancing the efficiency of electric planning, budget preparation, and network performance [14,15].…”