Short Term Price Forecasting Using Adaptive Generalized Neuron Model

Short Term Price Forecasting Using Adaptive Generalized Neuron Model

Nitin Singh (Motilal Nehru National Institute of Technology (MNNIT) Allahabad, Allahabad, India) and S. R. Mohanty (Motilal Nehru National Institute of Technology (MNNIT) Allahabad, Allahabad, India)
Copyright: © 2018 |Pages: 13
DOI: 10.4018/IJACI.2018070104
OnDemand PDF Download:
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

This article described how in the competitive deregulated electricity market forecasting has become one of the essential planning tool that assists the planners in preparing the power systems for future demands. The commercial success of the market players depends on their competitive bidding strategy which is suffuicient enough to meet the regulatory requirements and minimize the cost. Artificial neural networks due to their capability of non-linear mapping finds extensive application in the field of price forecasting. Although, they are extensively used as forecasting model, they have certain limitations which are detrimental to system performance. The training time of the artificial neural network is affected by the complexity of the system, and moreover, they require a large amount of data for complex problems. The worl presented in this article deals with the application of the generalized neuron model for forecasting the electricity price. The generalized neuron model overcomes the limitation of the conventional ANN. The electricity price of the New South Wales electricity market is forecast to test the performance of the proposed model. The free parameters of the proposed model are trained using fuzzy tuned genetic algorithms to increase efficacy of the model.
Article Preview
Top

Introduction

The forecasting has always been the major interest area of the electricity utilities and regulatories authorities across the world. The electricity industry of the developed nations have restructure the power systems by replacing the traditional “vertically integrated” monopolies with wholesale electricity markets. In these deregulated markets the market players bids for purchasing or selling the electricity and it is assumed that it will bring the electricity price down in the long run. The main focus of the restructured markets is to ensure continuity of supply at minimal cost for the economic and industrial growth. Forecasting plays an important role in assisting the decision makers and market players for designing the future power system according to their need (Shahidehpour et al., 2002; Aggarwal et al., 2009).

The load schedules were optimized by the consumers with the help of electricity price forecasting and on the other hand the generation companies maximize their profit using electricity price forecast (Catalão et al., 2007). The highly volatile nature of the electricity price posses the major challenge in forecasting it accurately for the planning and operation of competitive market. More uncertainity and complexity is added to the power system operation which consequetely affects the overall behaviour of generation, transmission and demand side in the deregulated market. Moreover, in order to ensure the stability of the grid the input power must always be equal to the consumed power taking critical /non-critical loads with all the dynamics being taken into consideration. The forecasting of electricity price is difficult as compared to the load forecasting and this is mainly due to the characteristics (i.e., multiple seasonality, high volatility, mean reversion, etc.) possessed by the price series.

The electricity prices are governed by the price spikes which are short-lived and much higher in magnitude as compared to the other commodities which also show jumps in their price. The price spikes can be negative or positive, the negative prices usually occurs due to the intermittent in-feed of the renewable wind energy which creates the surplus supply in the market and as in real time, since, the supply and demand need to be balanced in real time the electricity price becomes negative. The positive spikes which are more prominent are caused when the demand becomes high and the available supply is insufficient to meet the demand. The Volatility shown by the electricity spot prices is not constant but highly variable and clustered. In order to ensure the well-functioning power systems operation and market a reliable, efficient and accurate price forecasting tool is important (Contreras et al., 2003). The electricity price forecasting tool will also help the market operators to compute various parameters that will help in monitoring the market (Hong and Hsiao, 2002).

Comprehensive research does exist in context of the electricity price forecasting for making the power system planning more reliable and efficient. Accurate price forecast not only helps the independent generators for setting up optimal bidding patterns but also helps them in designing physical bilateral contracts and deciding to invest in augmenting their future generation facilities (Hu et al., 2009). Various models for forecasting the electricity prices have been developed in the past. The existing models are categorized into these two categories by various researchers, i.e., time series models and simulation based models. Time series models are again classified as linear and non-linear time series models (Koshiyama et al., 2012). The linear time series models finds extensive application in the field of electricity price forecasting dur to their simplicity and ease of implementation. The linear time series models do suffer from limitation, of their inability to capture the implied volatility of the price series (Aggarwal et al., 2008; Abdullah, 2012; Quan-yin et al., 2014).

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 13: 6 Issues (2022): Forthcoming, Available for Pre-Order
Volume 12: 4 Issues (2021): 3 Released, 1 Forthcoming
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 2 Issues (2016)
Volume 6: 2 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing