TY - JOUR
T1 - Application of a fuzzy model for short-term load forecast with group method of data handling enhancement
AU - Huang, Shyh Jier
AU - Shih, Kuang Rong
N1 - Funding Information:
The authors are greatly indebted to Taiwan Power Company for providing their valuable operating experience and system data. This work was partially supported by the National Science Council of Republic of China under contract number NSC88-2213-E-006-075, and sponsored by Taiwan Power Company under the contract number NSC88-TPC-E-006-013.
PY - 2002/10
Y1 - 2002/10
N2 - In this paper, a fuzzy model with the enhancement of group method of data handling is applied for short-term load forecast of a power system. In the approach, the group method of data handling is applied to formulate a fitting function that finds the relationship between linguistic values of input and output. Suitable inputs can be thus determined such that the number of redundant inputs is reduced. Moreover, as the properties of input variables are embedded with the weighting values of output, additional efforts of adjusting parameters of fuzzy membership functions can also be saved. The salient feature of this method lies in that an unknown system can be modeled at ease with a fewer number of rules, thereby reducing the computation time. By performing the simulations through the utility data, test results demonstrate the effectiveness of the proposed method, hence solidifying the feasibility of the method for the application considered.
AB - In this paper, a fuzzy model with the enhancement of group method of data handling is applied for short-term load forecast of a power system. In the approach, the group method of data handling is applied to formulate a fitting function that finds the relationship between linguistic values of input and output. Suitable inputs can be thus determined such that the number of redundant inputs is reduced. Moreover, as the properties of input variables are embedded with the weighting values of output, additional efforts of adjusting parameters of fuzzy membership functions can also be saved. The salient feature of this method lies in that an unknown system can be modeled at ease with a fewer number of rules, thereby reducing the computation time. By performing the simulations through the utility data, test results demonstrate the effectiveness of the proposed method, hence solidifying the feasibility of the method for the application considered.
UR - http://www.scopus.com/inward/record.url?scp=0036778976&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0036778976&partnerID=8YFLogxK
U2 - 10.1016/S0142-0615(01)00081-3
DO - 10.1016/S0142-0615(01)00081-3
M3 - Article
AN - SCOPUS:0036778976
SN - 0142-0615
VL - 24
SP - 631
EP - 638
JO - International Journal of Electrical Power and Energy Systems
JF - International Journal of Electrical Power and Energy Systems
IS - 8
ER -