Over the past several decades, many techniques and approaches have been proposed and implemented for load and price forecasting. The objective of all of these methods was load and price forecasting with minimal error. However, researchers face several challenges in achieving this goal. For price forecasting, the main challenge is to forecast electricity prices accurately in a deregulated electric power market with volatile aspects. Decentralized or deregulated markets are very volatile systems. Hence, pattern following and accurate forecasting of electricity prices are difficult tasks using ordinary methods. In this thesis, a novel approach is introduced and implemented to overcome the challenges inherent in accurate price forecasting. This novel approach involves innovations in forecasting to improve the spot power price forecasting accuracy in a competitive market. To investigate the applicability and effectiveness of this technique, Multiple Linear Regression (MLR) and Artificial Neural Networks (ANN), two well-known forecasting techniques, are developed.

Orientador: Carlos Alberto de Castro Júnior / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Elétrica e de Computação / Made available in DSpace on 2018-08-21T03:54:49Z (GMT). No. of bitstreams: 1 Tomiyama_EliasKento_M.pdf: 3080864 bytes, checksum: 7293fe7b3271c5c27e9b967c48a4e245 (MD5) Previous issue date: 2012 / Resumo: Esta dissertação de mestrado apresenta quatro metodologias de alocação de custos da transmissão: Pro rata (PR), Divisão Proporcional (PS), Zbus-médio (Zbus_AVG) e Nodal. Enquanto a primeira desconsidera o aspecto locacional e aloca os custos baseado apenas na quantidade de potência produzida pelos geradores e consumida pelas cargas, as últimas três levam em conta este aspecto, ou seja, as tarifas pagas por geradores e cargas dependem do seu ponto de conexão na rede elétrica. Através de simulações computacionais são levantadas várias situações de operação no sentido de avaliar a influência e as possíveis implicações de ordem regulatória, política, econômica e social de um país provocadas pela inclusão do aspecto locacional na definição das tarifas de uso do sistema de transmissão. Por fim, mostra-se a possibilidade de se considerar as tarifas pagas pelos agentes do sistema como um critério de decisão a mais no problema do planejamento da expansão da transmissão / Abstract: This dissertation describes four transmission cost allocation methodologies: Pro rata (PR), Proportional sharing (PS), Zbus-average (Zbus_AVG) and Nodal. While the first one disregards the locational aspect and allocates costs based only on the amount of power delivered by generators and consumed by loads, the last three ones take this aspect into account, i.e. charges are dependent on where generators and demands are connected in the network. Several computer simulations were made in order to assess the influence of the locational aspect into transmission pricing scheme and the results were used for a critical analysis, including political, regulatory, economic and social aspects. Finally, we discuss the possibility of using the fees paid by transmission system agents as an additional criterion for the Transmission Expansion Planning problem / Mestrado / Energia Eletrica / Mestre em Engenharia Elétrica