Application of a hybrid model based on multiple linear regression -principle component analysis (MLR-PCA) for electricity export forecasting

International electricity trade as a strategic commodity plays prominent role in the foreign market of countries. Electricity export forecasting leads to better production planning, supply security, blackouts reduc-tion, and obligations fulfillment. This paper aimed provide model for forecasting. In this regard, consumption different consumer sectors, gas consumption, population, GDP, electric-ity prices have been entered into multiple regression predictor variables. Although R2 =.976, F=66.110, SIG<.05 indicate appropriateness, high correlation between variables created collinearity. other words, Tolerance, VIF (variance inflation factor), Eigenvalue Condition Index are less than .2, more 10, close zero, 15 respectively. To solve problem, two hybrid methods Multiple Regression-First Difference Function Regression-PCA used. first method (R2 =.553) Tolerance index still show presence second =.936, F=169.9, SIG<.05) due all mentioned indicators, collinearity has completely resolved. So, MLR-PCA is most appropriate The data collected from Iran used illustrate model.