• PDF / 294,218 Bytes
• 10 Pages / 439.37 x 666.142 pts Page_size
• 101 Downloads / 231 Views

DOWNLOAD

REPORT

Abstract Deregulation in the electricity industry has made price forecasting the basis for maximizing profit of the different market players in the competitive market. The profit of market player depends on the bidding strategy and the successful bidding strategy requires accurate price forecasting of electricity price. The existing methods of price forecasting can be broadly classified into (i) statistical methods (ii) simulation-based methods and (iii) soft computing methods. The conventional neural networks were used for price forecasting due to their ability to find an accurate relation between the historical data and the forecasted price without any system knowledge. They suffer from major drawbacks like training time dependency on complexity of the system, huge data requirement, ANN structure is not fixed, hidden neurons requirement is large relatively, local minima. In the proposed work, the problems associated with conventional ANN trained using back-propagation are solved using improved generalized neuron model. The genetic algorithm along with fuzzy tuning is used for training the free parameters of the proposed forecasting model.

⋅

Keywords Generalized neural network Genetic algorithm transforms Fuzzy systems electricity price forecasting

⋅

⋅

Wavelet

1 Introduction The deregulation of electricity market has ensured the reliable electricity supply at reasonable cost for economic and industrial growth. Market players use price forecasting as a tool to manage the risk in deregulated electricity market [1, 2]. Bulk electricity consumers can maximize their load schedules while generation companies maximize their profit using accurate price forecasting. In case of vertically N. Singh (✉) ⋅ S.R. Mohanty Department of Electrical Engineering, MNNIT Allahabad, Allahabad, India e-mail: [email protected] S.R. Mohanty e-mail: [email protected] © Springer Nature Singapore Pte Ltd. 2017 S.K. Bhatia et al. (eds.), Advances in Computer and Computational Sciences, Advances in Intelligent Systems and Computing 553, DOI 10.1007/978-981-10-3770-2_39

419

420

N. Singh and S.R. Mohanty

integrated electric industry, the electricity prices reflect the government policy and price forecasting was based on average costs [3] whereas, deregulated market being a customer-driven market, the price is set by the supply–demand relationship. In deregulated market, the supply–demand have to be balanced in real time which requires that the electricity price must be pre-estimated before real-time operation for maximizing profit. Price forecasting in addition to helping independent generators in setting up optimal bidding patterns also helps in designing physical bilateral contracts, market prices strongly affect the decision on investing a new generation facilities in the long run [4]. Various models for forecasting the electricity prices have been developed based on hard and soft computing techniques out of which the models based on artificial neural network gained popularity due to their capacity to map input–output relation without the

Recommend Documents

Short-Term Forecasting

147 40 233KB

Short Term Load Forecasting

177 64 5MB

A Novel Deep Learning Ensemble Model with Secondary Decomposition for Short-Term Electricity Price Forecasting

153 103 80MB

Short-Term Demand Forecasting of Shared Bicycles Based on Long Short-Term Memory Neural Network Model

210 74 88MB

Using deep learning for short-term load forecasting

163 46 1MB

Short-term water demand forecasting using hybrid supervised and unsupervised machine learning model

224 86 2MB

Short-Term Wind Speed Forecasting Based on PSO-ELM

143 92 48MB

Convolutional residual network to short-term load forecasting

185 0 3MB

A Short Term Load Forecasting Based on Bagging-ELM Algorithm

190 82 26MB

Recurrent Neural Networks for Short-Term Load Forecasting An Overvie

216 27 3MB

A Novel Combined Model for Short-Term Electric Load Forecasting Based on Whale Optimization Algorithm

175 110 2MB

Long short-term memory-singular spectrum analysis-based model for electric load forecasting

167 66 3MB