Electricity Market Price Forecasting: Neural Networks versus Weighted-Distance k Nearest Neighbours

In today’s deregulated markets, forecasting energy prices is becoming more and more important. In the short term, expected price profiles help market participants to determine their bidding strategies. Consequently, accuracy in forecasting hourly prices is crucial for generation companies (GENCOs) t...

Descripción completa

Detalles Bibliográficos
Autores: Troncoso Lora, Alicia, Riquelme Santos, José Cristóbal, Riquelme Santos, Jesús Manuel, Martínez Ramos, José Luis, Gómez Expósito, Antonio
Tipo de recurso: capítulo de libro
Estado:Versión publicada
Fecha de publicación:2002
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/39159
Acceso en línea:http://hdl.handle.net/11441/39159
https://doi.org/10.1007/3-540-46146-9_32
Access Level:acceso abierto
Palabra clave:Data Structures
Cryptology and Information Theory
Artificial Intelligence (incl. Robotics)
Database Management
Information Storage and Retrieval
Information Systems Applications (incl. Internet)
Multimedia Information Systems
Descripción
Sumario:In today’s deregulated markets, forecasting energy prices is becoming more and more important. In the short term, expected price profiles help market participants to determine their bidding strategies. Consequently, accuracy in forecasting hourly prices is crucial for generation companies (GENCOs) to reduce the risk of over/underestimating the revenue obtained by selling energy. This paper presents and compares two techniques to deal with energy price forecasting time series: an Artificial Neural Network (ANN) and a combined k Nearest Neighbours (kNN) and Genetic algorithm (GA). First, a customized recurrent Multi-layer Perceptron is developed and applied to the 24-hour energy price forecasting problem, and the expected errors are quantified. Second, a k nearest neighbours algorithm is proposed using a Weighted-Euclidean distance. The weights are estimated by using a genetic algorithm. The performance of both methods on electricity market energy price forecasting is compared.