Electricity result show that electricity prices are

Electricity pricing has gradually become a new emerging area of research, relative to electricity demandforecasting and electricity load forecasting problems.Deepak & Swarup (2011) used artificial neural networks (ANN) to forecast electricity prices in deregulatedopen market power market. A neural network method was implemented to predict a day-aheadmarket clearing prices (MCPs) for energy markets. “The structure of the neural network was a three-layerback propagation (BP) network”.

The main concept of their work was to use historical prices and otherestimated features (such as temperature and load forecast) in the future to “fit” and “extrapolate” theprices and quantities. An artificial intelligent method which combines fuzzy and recurrent neural network(RNN) was used to forecast location marginal price (LMP). Eight-month historical electricity prices wascollected, and the ANN was trained using six-month data, days with normal trend, small spikes and largespikes was tested for each month. Their result showed that model was efficient for normal trend days butcouldn’t capture days with price spikes.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!

order now

Guan et al (2001) and Bajpai et al (2004) make use of game-theory based model, their focus was onthe impact of bidder behavior on electricity prices. The result show that electricity prices are related tothe “pricing” and “bidding” strategies of market players.Barlow (2002) studied a diffusion model for electricity pricing, he proposed a version of the modifiedgeometric Brownian motion as a jump diffusion model for stochastic modeling of electricity prices. Thefinding shows that in terms of performance, the geometrical mean reverting jump-diffusion models gives anaccurate result and models with no jumps seems to be unsuitable for electricity price modelling.

However,the drawback of this method is that it is tedious to incorporate physical characteristics of power systeminto mathematical models as it can lead to contradiction between the real power market and model outputs.Voronin et al. (2013) worked on driving an approach which will be able to predict a day-ahead electricityprices with the incorporation of price spikes.

“The price forecasting methodology was proposedusing a hybrid model”.


I'm Mary!

Would you like to get a custom essay? How about receiving a customized one?

Check it out