PSO BASED UNIT COMMITMENT
seminar surveyer Active In SP Posts: 3,541 Joined: Sep 2010 
28122010, 12:04 PM
Under the guidance of Mr. Rajesh Kumar Submitted by  Hitesh  Chandan sood Sandeep kumar New Microsoft PowerPoint Presentation.ppt (Size: 2.22 MB / Downloads: 159) INTRODUCTION In the case of an electric power system, the total load on the system will generally be different during the different hours of the day. If we are to supply a certain load, what unit or combination of units should be used to supply this load most economically comes under unit commitment problem. There are different approaches of solving the unit commitment problem i.e. Deterministic and In deterministic. In this project and implimentation we are using PARTICLE SWARM OPTIMISATION technique for solving the unit commitment problem. UNIT COMMITMENT Unit Commitment refers to the strategic choice to be made in order to determine which of the available power plants should be considered to supply electricity. It prepares a set of plants and stipulates in which time period they have to be online and ready for dispatching. Unit commitment problem in a power system involves determining a start up and shut down schedule of units to be used to meet the forecasted demand, over a future short term period(24168 hours). Constraints in Unit Commitment Spinning reserve Minimum up time Minimum down time Crew constraints PSO The objective of our project and implimentation is to present a Particle Swarm Optimization (PSO) based algorithm for unit commitment while satisfying demand and other equality and other inequality constraints. Particle Swarm Optimization is a population based stochastic optimization, developed by James Kennedy and Russell Eberhart in 1995 ,in which members within a group share the information among them to achieve the global best position. PSO ALGORITHM A swarm consists of a set of particles, where each particle represents a potential solution. Particles are then flown through the hyperspace, where the position of each particle is changed according to its own experience and that of its neighbours. Let xi (t) denotes the position of particle pi in search space, at time step t. The position of pi is then changed by adding a velocity vi (t) to the current position. The velocity vector drives the optimization process and reflects the socially exchanged information. Three different phases are differing: 


