28-06-2012, 03:57 PM
A System Marginal Price Forecasting Based on an Artificial Neural Network Adapted with Rough Set Theory
[attachment=25972]
INTRODUCTION
THE electric power industry in many countries all over the
world has been undergoing deregulation, privatization and
restructuring through the introduction of competition. Korea
has been keeping pace with this situation. Restructuring of
electric power industry in Korea started with the
establishment of the Korea Power Exchange (KPX) in April
2001, and the breakup of the generation sector from the Korea
Electric Power Corporation (KEPCO) into six generation
companies (GENCOs). Currently, Cost-Based Pool (CBP)
electricity market is in operation.
ROUGH SET THEORY
Rough Set Theory was developed by Pawlak in the early
1980’s [5],[6]. The concept of the Rough Set is a new
mathematical approach to imprecision, vagueness and
uncertainty in data analysis. The Rough Set philosophy is
founded on the assumption that with every object of the
universe of discourse we associate some information [7].
ARTIFICIAL NEURAL NETWORKS
Many researchers have been studying human brain in order
to realize a machine that can compute, judge and recognize
like a human being. Artificial neural network (ANN), which
mimics the human brain, has drawn much attention recently,
because its massive parallel structure can be utilized in
computation, which is much more efficient than in the
traditional serial-type computer. ANN is applied in many field
of study such as pattern recognition, noise filtering,
forecasting, etc. [1]. In power systems, ANNs have already
been used to solve problems such as load forecasting [13],
component and system fault diagnosis, security assessment,
unit commitment, etc. [9].
[attachment=25972]
INTRODUCTION
THE electric power industry in many countries all over the
world has been undergoing deregulation, privatization and
restructuring through the introduction of competition. Korea
has been keeping pace with this situation. Restructuring of
electric power industry in Korea started with the
establishment of the Korea Power Exchange (KPX) in April
2001, and the breakup of the generation sector from the Korea
Electric Power Corporation (KEPCO) into six generation
companies (GENCOs). Currently, Cost-Based Pool (CBP)
electricity market is in operation.
ROUGH SET THEORY
Rough Set Theory was developed by Pawlak in the early
1980’s [5],[6]. The concept of the Rough Set is a new
mathematical approach to imprecision, vagueness and
uncertainty in data analysis. The Rough Set philosophy is
founded on the assumption that with every object of the
universe of discourse we associate some information [7].
ARTIFICIAL NEURAL NETWORKS
Many researchers have been studying human brain in order
to realize a machine that can compute, judge and recognize
like a human being. Artificial neural network (ANN), which
mimics the human brain, has drawn much attention recently,
because its massive parallel structure can be utilized in
computation, which is much more efficient than in the
traditional serial-type computer. ANN is applied in many field
of study such as pattern recognition, noise filtering,
forecasting, etc. [1]. In power systems, ANNs have already
been used to solve problems such as load forecasting [13],
component and system fault diagnosis, security assessment,
unit commitment, etc. [9].