The article presents issues related to improving the accuracy of forecasting of combined electricity and heat production in a selected gas-fired CHP plant equipped with two gas turbines with heat exchangers and a heat accumulator. Currently, in the forecasting of energy carriers production, so-called correction curves of the gas turbine producer being used in CHP plants are applied. These curves are a calculation tool in the computer system of operation supervision in the module used to simulate the forecasting of electricity and heat production in a CHP plant. The experience gained so far from the operation of gas turbines indicates the differences between the forecasts of energy carriers production obtained using the values determined from correction curves and the actual values resulting from operational measurements from the distributed control system and energy balancing of the system. In order to improve the accuracy of forecasting the production of energy carriers in the considered CHP plant, it has been proposed to extend the existing computer system for supervising operation with an additional calculation module. The task of this module is to correct the forecasts for electricity and heat production obtained using mentioned before correction curves. In the additional computational module of the computer system it is proposed to use empirical functions developed with the use of operational measurements of the analyzed gas turbines. Due to the occurring measurement redundancy, advanced data validation and reconciliation of measurements in accordance with the methodology included in VDI 2048 guidelines was used. In the process of preparing the measurement data for the development of static empirical functions, the GLR (Generalized Likehood Ratio) algorithm was used to detect process changes. This algorithm allows to separate the steady-state periods of gas turbines operation. In the procedure of determining the mathematical form and coefficients of empirical functions, the cross-validation method was applied. The obtained results of the analyses confirm the possibility of their use in the existing computer system for supervision of the operation of a CHP plant, increasing the accuracy of planning the production of energy carriers.