Forecasting Electricity Consumption Using Function Fitting Artificial Neural Networks and Regression Methods
Authors:
- André GifalliAGAndré Gifalli
- Haroldo Luiz Moretti Do AmaralHAHaroldo Luiz Moretti Do Amaral
- Alfredo Bonini NetoAlfredo Bonini Neto
- André Nunes de SouzaASAndré Nunes de Souza
- André von Frühauf HublardAHAndré von Frühauf Hublard
- João Carlos CarneiroJCJoão Carlos Carneiro
- Floriano Torres NetoFloriano Torres Neto
Open Access
- 18 October 2024
- journal article
- research article
- Published by MDPI AG in Applied System Innovation
- Vol. 7 (5) , 100
Abstract
With the growth of smart grids, consumers now have access to new technologies that enable improvements in the quality of service provided and allow new levels of energy efficiency. Much of this increase in energy efficiency is directly related to changes in consumption habits due to the quantity and quality of information made available by new technologies. At this point, short-term consumption forecasting can be considered an effective information tool in the search for better consumption patterns and energy efficiency. This paper presents prediction tests combining the result obtained from an artificial neural network and regression methods. The artificial neural network used was the Multilayer Perceptron (MLP), and its results were compared with polynomial regression techniques (first, second, and third degree), demonstrating the superiority of the network. The neural network has proven to be a highly effective tool for forecasting future data, demonstrating its ability to capture complex patterns in input data and produce accurate estimates. Additionally, the flexibility of neural networks in handling large volumes of data and their continuous adjustment capability further enhance their suitability as a robust tool for future predictions. The results corroborate the capacity of the methodology presented for short-term consumption forecasting.Keywords
Funding Information
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (88887.704285/2022-00)
This publication has 19 references indexed in Scilit:
- Electricity Demand Forecasting Using a Novel Time Series Ensemble TechniqueIEEE Access, 2024
- A Stochastic Bi-Level Optimal Allocation Approach of Intelligent Buildings Considering Energy Storage Sharing ServicesIEEE Transactions on Consumer Electronics, 2024
- Power Flow Control-Based Regenerative Braking Energy Utilization in AC Electrified Railways: Review and Future TrendsIEEE Transactions on Intelligent Transportation Systems, 2024
- Adaptive Optimal Greedy Clustering-Based Monthly Electricity Consumption Forecasting MethodIEEE Transactions on Industry Applications, 2022
- Machine Learning Algorithms for Short-Term Load Forecast in Residential Buildings Using Smart Meters, Sensors and Big Data SolutionsIEEE Access, 2019
- Day-ahead aggregated load forecasting based on two-terminal sparse coding and deep neural network fusionElectric Power Systems Research, 2019
- Recuperation of Regenerative Braking Energy in Electric Rail Transit SystemsIEEE Transactions on Intelligent Transportation Systems, 2019
- Artificial neural network based day ahead load forecasting using Smart Meter data2016
- Smart meters as a tool for energy efficiency2014
- The Kernel Recursive Least-Squares AlgorithmIEEE Transactions on Signal Processing, 2004