Forecasting techniques for deregulated electricity market prices

Abstract

This paper reports preliminary results of an ongoing survey of electricity price forecasting techniques developed over the last fifteen years or so. The main focus of this survey is the method of forecasting electrical energy prices on a pool-style energy forward market (typically, one-day ahead). Because the British market began operating its initial pool and real data became available in 1990, this survey reviewed publications that appeared in 1990 and after. The paper source of this preliminary survey is exclusively limited to INSPEC/IEEE-Xplore. A limited list of printed books for general background information is also included. From the review of the papers, a summary of general procedure of price forecasting and of factors to be considered is discussed.

Power management in heterogeneous networks with energy harvesting base stations

“…The real-time price of electricity can be forecasted using price forecast techniques such as the ones proposed in [29]. Similar to the renewable energy model, we assume that the real-time price of energy of time slot t, denoted as C(t), is the sum of an accurately predicted mean valueĈ(t) and i.i.d.…”

Price forecasting using wavelet transform and LSE based mixed model in Australian electricity market

“…But price forecasting in these markets is a difficult task since it depends upon a number of factors like power demand, excess demand or supply shortfall, fuel prices, market design, bidding strategies of the participants, etc. (Niimura, 2006).…”

Integrating plug-in electric vehicles into the electric power system

“…The proposed methods require that the aggregator utilizes techniques for forecasting the day-ahead electricity price, such as the ones presented in [57][58][59][60]. Herein, it is assumed that day-ahead locational marginal price (LMP) can be forecasted with reasonable accuracy, and the error associated with the forecast is ignored.…”

“…To achieve this, it is assumed that the aggregator utilizes advanced forecasting techniques for the day-ahead electricity locational marginal prices (LMPs), such as the ones presented in [57][58][59][60]. It is important to note that the LMP forecast's absolute value is not critical.…”

“…If the PEV load makes the price reach the level of the third cheapest price, then any additional PEV load will be distributed over these three hours, and so forth. The use of advanced day-ahead LMP forecasting algorithms, such as the ones in [57][58][59][60], will be again necessary.…”