Abstract
In the electric power market, power system marginal price forecasting is the basis for power companies to build their optimal bidding strategies. Price forecasting is a new research area, because power market is still in the rudimentary stage in China. Due to its attractive properties of learning convergence and speed, many practical areas have widely put it into use including power system marginal price forecasting area. The method of neural network is good at its learning capability but lack of clear internal knowledge expression. The beginning of study is limited to random initial conditions, which may lead to low convergence speed and even local extremum. Necessary initial experience and knowledge cannot be fully made use of. While fuzzy logic method is good at approximate and qualitative knowledge expression but lack of learning capability. Membership function and fuzzy rules can only be selected by experience and tries. Besides, the study and adjustment of parameters and weigh is rather difficult. Thus, the proper combination of the above methods is a breakthrough in effective system control. This paper establishes a short-term forecasting model of power system marginal price using the method of cerebellar model articulation controller neural network, and applies it to power market in real province for training and examining. FCMAC method is proved to be superior to former methods, for its low need of training samples, its stable outputs, its high forecasted speed and accuracy. This method provides power companies with a reliable support in making and implementing their bidding strategies.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.