A fuzzy-neural approach to electricity load and spot price forecasting in a deregulated electricity market

Iyer, Vasanth; Fung, Chum Che; Gedeon, Tamás D.

doi:10.1109/tencon.2003.1273164

Cited by 21 publications

(5 citation statements)

References 5 publications

(1 reference statement)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, first NN approaches were proposed (Wang and Ramsay, 1997) and applied for the existing energy pools. They were followed by different structures on NNs (Mendes et al, 2007;Yang and Sun, 2008;Akole et al, 2011), radial basis functions (Meng et al, 2009), recursive NNs (Mandal et al, 2007) and hybrid approaches of fuzzy NNs (Iyer et al, 2003) and with wavelets (Giri et al, 2010). Reports show that hybrid approach of wavelets and NNs called AWNN (Bhaskar and Singh, 2012) is an interesting alternative.…”

Section: Electricity Prices Prediction Taskmentioning

confidence: 99%

Alternative approaches to the prediction of electricity prices

Domański

Gintrowski

2017

IJESM

View full text Add to dashboard Cite

Purpose This paper aims to present the results of the comparison between different approaches to the prediction of electricity prices. It is well-known that the properties of the data generation process may prefer some modeling methods over the others. The data having an origin in social or market processes are characterized by unexpectedly wide realization space resulting in the existence of the long tails in the probabilistic density function. These data may not be easy in time series prediction using standard approaches based on the normal distribution assumptions. The electricity prices on the deregulated market fall into this category. Design/methodology/approach The paper presents alternative approaches, i.e. memory-based prediction and fractal approach compared with established nonlinear method of neural networks. The appropriate interpretation of results is supported with the statistical data analysis and data conditioning. These algorithms have been applied to the problem of the energy price prediction on the deregulated electricity market with data from Polish and Austrian energy stock exchanges. Findings The first outcome of the analysis is that there are several situations in the task of time series prediction, when standard modeling approach based on the assumption that each change is independent of the last following random Gaussian bell pattern may not be a true. In this paper, such a case was considered: price data from energy markets. Electricity prices data are biased by the human nature. It is shown that more relevant for data properties was Cauchy probabilistic distribution. Results have shown that alternative approaches may be used and prediction for both data memory-based approach resulted in the best performance. Research limitations/implications “Personalization” of the model is crucial aspect in the whole methodology. All available knowledge should be used on the forecasted phenomenon and incorporate it into the model. In case of the memory-based modeling, it is a specific design of the history searching routine that uses the understanding of the process features. Importance should shift toward methodology structure design and algorithm customization and then to parameter estimation. Such modeling approach may be more descriptive for the user enabling understanding of the process and further iterative improvement in a continuous striving for perfection. Practical implications Memory-based modeling can be practically applied. These models have large potential that is worth to be exploited. One disadvantage of this modeling approach is large calculation effort connected with a need of constant evaluation of large data sets. It was shown that a graphics processing unit (GPU) approach through parallel calculation on the graphical cards can improve it dramatically. Social implications The modeling of the electricity prices has big impact of the daily operation of the electricity traders and distributors. From one side, appropriate modeling can improve performance mitigating risks associated with the process. Thus, the end users should receive higher quality of services ultimately with lower prices and minimized risk of the energy loss incidents. Originality/value The use of the alternative approaches, such as memory-based reasoning or fractals, is very rare in the field of the electricity price forecasting. Thus, it gives a new impact for further research enabling development of better solutions incorporating all available process knowledge and customized hybrid algorithms.

show abstract

Section: Electricity Prices Prediction Taskmentioning

confidence: 99%

Alternative approaches to the prediction of electricity prices

Domański

Gintrowski

2017

IJESM

View full text Add to dashboard Cite

show abstract

“…The extant literature also shows that there are multiple similarities between variable pricing electricity market and variable pricing cloud computing. The auction based cloud model has been influenced extensively by variable pricing electricity market [9][10][11][12][13]. There are multiple of similarities among the above mentioned markets.…”

Section: Background Of Auction Based Cloud Modelmentioning

confidence: 99%

Dynamic Price Prediction for Amazon Spot Instances

Singh

Dutta

2015

2015 48th Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Variable pricing cloud resources are the most recent advancement in cloud computing business models. Cloud vendors like Amazon Web Services, a.k.a. Amazon AWS provide a new cloud instance type known as "Spot instance". The distinguishing feature of spot instance is its dynamic pricing. The price of spot instances varies dynamically with time based on demand and supply of cloud resources in the datacenters across the globe. Customers place bids to obtain spot instances using an online auction platform. The auction platform determines the market clearance price, a.k.a. "Spot price" and the users whose bids are above the aforementioned price obtain the instances. Cloud vendors provide current and archived spot price data to assist their customers in bidding process. The major challenge for the customers in this new business model is to predict the spot price before placing their bids. In this paper, we have provided a novel algorithm for spot price prediction. We also have instantiated and demonstrated the proposed algorithm. The results show high accuracy of 9.4% Mean Absolute Percent Error (MAPE) for short term (one day ahead) and less 20% MAPE for long term (five days ahead) forecasting.

show abstract

“…(i) statistical models [1,2,6] (ii) artificial neural network (ANN) [3][4][5][6][7][8] Espinola, et al presented dynamic regression and transfer function models in California and Spanish markets [1]. They demonstrated that their methods gave better prediction accuracy than the ARIMA model.…”

Section: Introductionmentioning

confidence: 99%

“…They employed the three-layer perceptron as ANN. Afterwards, ANN and/or fuzzy inference based methods have been developed [5][6][7][8]. However, the conventional methods have a drawback that they are inclined to give larger prediction error due to high volatility of nonlinear time series.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Normalized Radial Basis Function Network with Hierarchical Deterministic Annealing for Electricity Price Zone Forecasting

Mori

Awata

2006

2006 IEEE International Conference on Systems, Man and Cybernetics

View full text Add to dashboard Cite

In this paper, a new method is proposed for electricity price zone forecasting. The proposed method employs the normalized radial basis function network that modifies the radial basis function network by the normalization technique, uses hierarchical deterministic annealing clustering to determine the center of NRBFN. Also, clipping is used for output of NRBFN to simplify the problem whether one-step-ahead price zone exceeds a threshold value. Furthermore, a set of threshold are prepared to construct a binary tree that classifies the price zone into clusters. The proposed method is successfully applied to real data of ISO New England.

show abstract

A fuzzy-neural approach to electricity load and spot price forecasting in a deregulated electricity market

Cited by 21 publications

References 5 publications

Alternative approaches to the prediction of electricity prices

Alternative approaches to the prediction of electricity prices

Dynamic Price Prediction for Amazon Spot Instances

Normalized Radial Basis Function Network with Hierarchical Deterministic Annealing for Electricity Price Zone Forecasting

Contact Info

Product

Resources

About