Electricity market price spike forecast with data mining techniques

Electricity market price forecast is a changeling yet very important task for electricity market managers and participants. Due to the complexity and uncertainties in the power grid, electricity prices are highly volatile and normally carry with spikes. which may be (ens or even hundreds of times higher than the normal price. Such electricity spikes are very difficult to be predicted. So far. most of the research on electricity price forecast is based on the normal range electricity prices. This paper proposes a data mining based electricity price forecast framework, which can predict the normal price as well as the price spikes. The normal price can be, predicted by a previously proposed wavelet and neural network based forecast model, while the spikes are forecasted based on a data mining approach. This paper focuses on the spike prediction and explores the reasons for price spikes based on the measurement of a proposed composite supply-demand balance index (SDI) and relative demand index (RDI). These indices are able to reflect the relationship among electricity demand, electricity supply and electricity reserve capacity. The proposed model is based on a mining database including market clearing price, trading hour. electricity), demand, electricity supply and reserve. Bayesian classification and similarity searching techniques are used to mine the database to find out the internal relationships between electricity price spikes and these proposed. The mining results are used to form the price spike forecast model. This proposed model is able to generate forecasted price spike, level of spike and associated forecast confidence level. The model is tested with the Queensland electricity market data with promising results. Crown Copyright (C) 2004 Published by Elsevier B.V. All rights reserved.

Assessing the competitiveness of loss allocation methods in a deregulated electricity market

This paper critically assesses several loss allocation methods based on the type of competition each method promotes. This understanding assists in determining which method will promote more efficient network operations when implemented in deregulated electricity industries. The methods addressed in this paper include the pro rata [1], proportional sharing [2], loss formula [3], incremental [4], and a new method proposed by the authors of this paper, which is loop-based [5]. These methods are tested on a modified Nordic 32-bus network, where different case studies of different operating points are investigated. The varying results obtained for each allocation method at different operating points make it possible to distinguish methods that promote unhealthy competition from those that encourage better system operation.

A framework for electricity price spike analysis with advanced data mining methods

There are many techniques for electricity market price forecasting. However, most of them are designed for expected price analysis rather than price spike forecasting. An effective method of predicting the occurrence of spikes has not yet been observed in the literature so far. In this paper, a data mining based approach is presented to give a reliable forecast of the occurrence of price spikes. Combined with the spike value prediction techniques developed by the same authors, the proposed approach aims at providing a comprehensive tool for price spike forecasting. In this paper, feature selection techniques are firstly described to identify the attributes relevant to the occurrence of spikes. A simple introduction to the classification techniques is given for completeness. Two algorithms: support vector machine and probability classifier are chosen to be the spike occurrence predictors and are discussed in details. Realistic market data are used to test the proposed model with promising results.

What are the economic prospects of developing aquaculture in Queensland to supply the low price white fillet market? Lessons from the US channel catfish industry

The farming of channel catfish (Ictalurus punctatus) is the largest (by volume and value) and most successful (in terms of market impact) aquaculture industry in the United States of America. Farmed channel catfish is the most consumed (in terms of volume per capita) fish fillet in the U.S. market. Within Australia, it has long been suggested by researchers and industry that silver perch (Bidyanus bidyanus) and possibly other endemic teraponid species possess similar biological attributes for aquaculture as channel catfish and may have the potential to generate a similar industry. The current teraponid industry in Australia, however, shows very little resemblance to the catfish industry, either in production style or market philosophy. A well established budget framework from the literature on U.S. channel catfish farming has been adapted for cost and climate conditions of the Burdekin region, Queensland, Australia. Breakeven prices for the hypothetical teraponid farms were found to be up to 50% higher than those published for catfish farms however were much lower than those reported for silver perch production in Australia using current, endemic styles of production. The breakeven prices for the hypothetical teraponid farms were most sensitive (in order of significance) to feed prices, production rates, interest rates, fingerling prices and electricity prices. At equivalent feed costs the costs of production between the hypothetical catfish farms in the Mississippi, U.S. and the hypothetical teraponid farms in the Burdekin, Australia were remarkably similar. The cost of feeds suitable for teraponid production in Australia are currently around double that of catfish feeds in the U.S. Issues currently hindering the development of a large scale teraponid industry in Australia are discussed.

Overcoming original antigenic sin to generate effective immune responses in antigen primed host

Original antigenic sin is failure to mount effective immunity to virus variants in a previously virus infected host. We have previously shown that prior immunity to a virus capsid protein inhibits induction from naive CD8 T cells of an IFN-g response to a MHC class I restricted epitope linked to the capsid protein, following immunisation with a capsid expressing the class I restricted epitope. The inhibition is independent of pre-existing antibody to the viral capsid, and the inhibition is observed in animal lacking B cells. CD8 restricted viral capsid specific T cell responses are also not required, but the inhibition is not observed in IL10 knockout mice. We now demonstrate that capsid antigen primed CD4+ T cells secrete IL10 in response to capsid antigen presented by DC, and deviate CD8 cells specific for the linked MHC Class I restricted epitope from IFN-g production to IL-5 production. Neutralizing IL10, either in vitro or in vivo, restores induction following immunisation of an antigen specific IFN-g response to an MHC Class I restricted epitope. This finding demonstrates a strategy for overcoming bias towards a Tc2 response to MHC Class I epitopes upon immunisation of a host already primed to antigen, facilitating immunotherapy for chronic viral infection or cancer