scispace - formally typeset
Search or ask a question
Book ChapterDOI

Prediction of Market Power Using SVM as Regressor Under Deregulated Electricity Market

TL;DR: In this paper, the effectiveness of SVM technique in predicting market power is formulated and linear and nonlinear kernels are compared.
Abstract: This paper proposes a methodology to utilize support vector machines (SVM) as a regressor tool for predicting market power. Both the companies, i.e., Generation (Gencos) and the Distribution (Discos), can utilize this tool to forecast market power on their perspective. Attributes and criterion are to be chosen properly to classify market power. In this paper, the effectiveness of SVM technique in predicting market power is formulated. Independent system operator (ISO) can also use this tool as regressor and it is discussed elaborately. Both linear and nonlinear kernels are compared. Nodal must run share (NMRS) is used as an index for predicting market power. A sample of three-bus system consisting of two generators and one load/two loads is used to illustrate the study.
References
More filters
Book
01 Jan 2000
TL;DR: This is the first comprehensive introduction to Support Vector Machines (SVMs), a new generation learning system based on recent advances in statistical learning theory, and will guide practitioners to updated literature, new applications, and on-line software.
Abstract: From the publisher: This is the first comprehensive introduction to Support Vector Machines (SVMs), a new generation learning system based on recent advances in statistical learning theory. SVMs deliver state-of-the-art performance in real-world applications such as text categorisation, hand-written character recognition, image classification, biosequences analysis, etc., and are now established as one of the standard tools for machine learning and data mining. Students will find the book both stimulating and accessible, while practitioners will be guided smoothly through the material required for a good grasp of the theory and its applications. The concepts are introduced gradually in accessible and self-contained stages, while the presentation is rigorous and thorough. Pointers to relevant literature and web sites containing software ensure that it forms an ideal starting point for further study. Equally, the book and its associated web site will guide practitioners to updated literature, new applications, and on-line software.

13,736 citations

Journal ArticleDOI
TL;DR: A novel method based on a combination of binary classifiers which are optimized for those special cases where the real signals contain a multitude of events within the analyzed temporal window, and can be implemented with low computational cost.
Abstract: The method classifies more than one PQ event within the same temporal window.The algorithm was based on Wavelet Transform and Support Vector Machine (SVM).The classification method uses One vs. One multiclass SVM.The algorithm was tested using several real PQ events obtained from the field.More than 92% of the measured PQ events were successfully detected and classified. In this paper we propose a method based on a combination of binary classifiers which are optimized for those special cases where the real signals contain a multitude of events within the analyzed temporal window. These type of events are known as complex events. The proposed Power Quality (PQ) classifier is based on Wavelet Transforms (WT) and Support Vector Machines (SVM). The method uses a One vs. One multiclass SVM. We propose a novel method which is simple, easy to train, and can be implemented with low computational cost. The proposed algorithm consists of a set of simple binary SVM classifiers. Each SVM node is trained separately allowing them to be parallelized. The training stage is performed using single events, however due to the structure of the SVM methodology selected, it allows the system to detect complex events. Tests and training were performed using real complex signals and the results show the proposed methodology to be highly efficient.

143 citations

Journal ArticleDOI
TL;DR: A comprehensive review on market power with various indices which were used in market power analysis and the evolution of research and development in the field of market power is presented in this paper, where the literature work presented in this paper has been divided into various sections to facilitate the upcoming researchers who carry out their research in the area of Market power under various environments.

119 citations

Journal ArticleDOI
TL;DR: In this article, a GA-SVM approach for online monitoring of long-term voltage instability has been proposed, which uses the voltage magnitude and phase angle obtained from Phasor Measurement Units (PMUs) as the input vectors to SVM and the output vector is the voltage Stability Margin Index (VSMI).

101 citations

Journal ArticleDOI
TL;DR: In this paper, the impact of load variation, the size of a power supplier and random failures on market power has been investigated, and the geographic difference of market power caused by network constraints has been considered.
Abstract: Market power assessment is an important aspect of electric market analysis and operation. Market power problems are more complicated in an electric market than those in other markets due to the specific properties of electricity. This paper investigates market power problems and the related solution techniques in an electric power market. The impact of load variation, the size of a power supplier and random failures on market power has been investigated. The geographic difference of market power caused by network constraints has been considered. Must run share (MRS) and nodal must-run share (NMRS) have been proposed to represent system and local market powers respectively. An optimization technique and the topological analysis of power flow have been used to determine the MRS and NMRS. Expected nodal must-run share (ENMRS) has been proposed to represent the impact of random failures on market power and the associated risk of customers paying a high price due to the exercise of market power. The contingency enumeration and probabilistic technique have been used to determine the ENMRS. The IEEE Reliability Test System is analyzed to illustrate the proposed indices and techniques.

100 citations