The problem of optimal distribution of the current load of a combined heat and power plant with a complex composition of equipment is considered. A multi-criteria approach is proposed for parts of graphs with a constant load in time, considering the factors of economy, reliability and ecology. For sections of the graph with a time-variable load, we consider the formulation of a dynamic optimization problem. In order to increase the intelligence of solving the tasks set, we propose a variant of building an intelligent system that, in addition to a number of intelligent functions, aims to: switch to the principle of advanced (predictive) control when performing the dispatching schedule of loads; select the number of criteria under consideration; evaluate the values of unmeasured or poorly measured parameters; identify the current technical condition of equipment, as well as recommend either a solution available in the database, or perform new calculations.