An improved cost estimation for unit commitment using back propagation algorithm

Abstract

The daily load is the main issue for many power plant industries that are affected by the varying maximum and minimum peak hours. Due to electricity being used less during the weekends, compared to weekdays, where the spending is higher. The same logic applies to day and night spending, which requires balancing among the units so that it can operate during high demand hours. The main problem is to determine the units that will be affected according to the operation schedule which means which unit, and for how long, will it stay on or off. In this context, the main objective for unit commitment, in general, minimizes the total cost of operating a unit, and at the same time maintain the constraints met. Several approaches and techniques used in existing studied, each have a solution for the optimal unit commitment problem. Some of the approaches presented, use complex methods in order to address the issues, while others use simple forms to do the same task. The problem of operation scheduling for unit commitment will be different depending on the type of industry, and according to the plan of mixing unit and operating constraints.