Estimating daily peak load using symmetrical doubly linear adaptive-fuzzy regression model

1.559 519


Abstract. One appropriate and efficient model to estimate daily peak load is using fuzzy regression models. In this article, two types of fuzzy regression models named linear fuzzy regression and doubly linear adaptive-fuzzy regression are worked on. We will demonstrate by a practical example that the variance of doubly linear adaptive-fuzzy regression model is always lower than the variance of linear fuzzy model. 


daily peak load, linear fuzzy regression, doubly linear regression, daily peak load estimation

Full Text:



Dr. Jann-Huei Jinn Department of Statistics G rand Valley State University Allendale, Michigan, 94401

Dr. Chowan-Chin Song and Mr. J. C. Chao Department of Applied Mathematics National Cheng-Chi University Taipei, Tavian, R.O.C. J.Andres Sanchez, “Claim reserving with fuzzy regression and Taylors geometric )3 Separation method “, insurance: Mathematics and Economics, 40, (2007), 145-163.

Andrés,, Terceno, A., 2003a. Applications of fuzzy regression in actuarial analysis.

Journal if Risk and Insurance 70 (4), 665-699. Buckley, P.L., Qu, Y., 1990. On using α-cuts to evaluate Fuzzy equations. Fuzzy Sets and Systems 29, 145-153

Derrig, R.A., Ostaszewski, K., 1998. Fuzzy sets methodologies in Actuarial Science. In:

Practical Applications of Fuzzy Technologies. Kluwer, Heidelberg, pp, 531-556. Dubois, D., Prade, H., 1993. Fuzzy numbers: An overview. In: Fuzzy Sets for Intelligent

Systems. Morgan Kaufmann Publishers, San Mateo (CA), PP. 113-148. Fedrizzi, M., Fedrizzi, M., Ostasiewicz, W., 1993. Towards fuzzy modeling in economics.

Fuzzy Sets and Systems 54, 259-268. Hojati, M., Bector, C.R., Smimou, K., 2005. A simple method for computation of fuzzy linear regression. European Journal of Operational Research 166, 172-184.

Salimiyan, Zohre. Amini, Farokh. Psc 2005.Application of fuzzy linear regression model to estimate the daily peak load a domestic feeder in Yazd. 20th international Power System Conference.