A developed short-term electricity price and load forecasting method based on data processing, support vector machine, a
- PDF / 1,459,795 Bytes
- 18 Pages / 547.087 x 737.008 pts Page_size
- 51 Downloads / 192 Views
ORIGINAL ARTICLE
A developed short-term electricity price and load forecasting method based on data processing, support vector machine, and virus colony search Ali Ghasemi-Marzbali
Received: 22 July 2019 / Accepted: 26 August 2020 / Published online: 10 September 2020 # Springer Nature B.V. 2020
Abstract Surely, electricity market participants need an accurate estimate for the price and load signals to properly manage their programs to increase their profits. Regarding the two-way interaction between suppliers and consumers, they are able to manage their required profile. Therefore, the individual price or load forecasting is not acceptable and cannot capture their related pattern. Therefore, this paper presents a new forecasting method for price and load signals in simultaneous configuration. This method consists of three main parts: the first part proposes two data preprocessing methods based on wavelet transform to remove noisy term and mutual information to select best features with maximum relevancy and minimum redundancy. The second part suggests a learning engine based on a least square support vector machine (LSSVM) with self-adaptive kernel functions and generalized autoregressive conditional heteroscedasticity (GARCH) time series to extract the linear and nonlinear patterns. Finally, the last part employs a new modified virus colony search algorithm (VCS) to efficiently set the LSSVM control parameters to use its all capacity. Simulations are carried out for three well-known Australia’s, New York’s, and Ontario’s electricity markets. The obtained results show the acceptable results.
A. Ghasemi-Marzbali (*) Department of Electrical and Biomedical Engineering, Mazandaran University of Science and Technology, Babol, Iran e-mail: [email protected]
Keywords Price/load forecast . Support vector machine . Optimization . Smart grid . Feature selection . Wavelet transform
Introduction Aims and difficulties The power system in the recent years is moving from vertically and monopolistic model to restructured, independent, and competitive structure (Ghasemi-Marzbali 2020a). Owing to the fast growing of advanced digital two-way power flow power system and create a flexible system where consumers can manage their demand by looking at the price under different uncertainties, a new concept appears which named smart grid. Consequently, this new concept considers all previous advantages and makes a better market for all participants (Dileep 2020). But, in this environment, all ancillary services are reconfigured and reformulated to correctly consider their inherent associations. Among them, price or load forecasting become more important since their accurate value directly effects on all participants’ future programs (Brown 2018). Most of the available price or load forecasting methods only focused on the individual forms without consider their interaction. Therefore, this paper tries to cover this gap presenting a new framework for a simultaneous price and load forecast. Shorting speaking and considering custome
Data Loading...
