A Hybrid Neural Network and Simulated Annealing Approach to the Unit Commitment Problem

Machine Learning Research Centre, School of Computer Science, QUT, Brisbane, Qld 4001, Australia
Source: OAI


In this paper, the authors present an approach combining the feedforward neural network and the simulated annealing method to solve unit commitment, a mixed integer combinatorial optimisation problem in power system. The artificial neural network (ANN) is used to determine the discrete variables corresponding to the state of each unit at each time interval. The simulated annealing method is used to generate the continuous variables corresponding to the power output of each unit and the production cost. The type of neural network used in this method is a multi-layer perceptron trained by the back-propagation algorithm. A set of load profiles as inputs and the corresponding unit-commitment schedules as outputs (satisfying the minimum up-down, spinning reserve and crew constraints) are utilized to train the network. A method to generate the training patterns is also presented. The experimental result demonstrates that the proposed approach can solve unit commitment in a reduced computational time with an optimum generation schedule.

Download full-text


Available from: Jaydev Sharma,
  • Source
    • "However, a great deal of operator interaction is required in this approach, making it inconvenient and time-consuming. Neural networks (most often multilayer perceptrons) are trained to recognize the most economical UC schedule associated with the pattern of the current load curve (Nayak & Sharma, 2000; Wong, Chung, & Wong, 2000). The training set contains typical load curves and corresponding UC schedules. "
    [Show abstract] [Hide abstract]
    ABSTRACT: An approach for solving the unit commitment problem based on genetic algorithm with binary representation of the unit start-up and shut-down times is presented. The proposed definition of the decision variables and their binary representation reduce the solution space and computational time in comparison to the classical genetic algorithm approach to unit commitment. The method incorporates time-dependent start-up costs, demand and reserve constraints, minimum up and down time constraints and units power generation limits. Penalty functions are applied to the infeasible solutions. Test results showed an improvement in effectiveness and computational time compared to results obtained from genetic algorithm with standard binary representation of the unit states and other methods.
    Expert Systems with Applications 11/2013; 40(15):6080–6086. DOI:10.1016/j.eswa.2013.05.010 · 2.24 Impact Factor
  • Source
    • "One of the decision making problems is related to the scheduling of the generators at any particular time in a power system. It is not economical to operate all the units necessary to satisfy the peak load during low load periods [5]. The principal aim of a power system is to minimize the power generation expenses while satisfying the hourly forecasted power demand. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Unit Commitment Problem (UCP) is a nonlinear mixed integer optimization problem used in the scheduling operation of power system generating units subjected to demand and reserve requirement constraints for achieving minimum operating cost. The task of the UC problem is to determine the on/off state of the generating units at every hour interval of the planning period for optimally transmitting the load and reserve among the committed units. The importance for the necessity of a more effective optimal solution to the UCP problem is increasing with the regularly varying demand. Hereby, we propose a hybrid approach which solves the unit commitment problem subjected to necessary constraints and gives the optimal commitment of the units. The possible combination of demand and their corresponding optimal generation schedule can be determined by the PSO algorithm. Being a global optimization technique, Evolutionary Programming (EP) for solving Unit Commitment Problem, operates on a method, which encodes each unit's operating schedule with respect to up/down time. When the demand over a time horizon is given as input to the network it successfully gives the schedule of each unit's commitment that satisfies the demands of all the periods and results in minimum total cost. Because hybridization is dominating, this approach for solving the unit commitment problem is more effective.
  • Source
    • "One main drawback and limiting factor of this method is that it takes a great deal of CPU time to find the near-optimal solution. In order to improve the performance, SA is combined with other methods: the genetic algorithm [25] [26] [27], the neural network [28], the tabu search [25], and the evolutionary programming [29]. This paper presents an adaptive SA algorithm to solve the UC problem. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents an approach for solving the unit commitment problem based on a simulated annealing algorithm with an adaptive schedule. The control parameter, temperature, is adapted to the cost levels on which the algorithm operates during the annealing process. This shortens the time taken to find a good solution meeting all constraints and improves the convergence of the algorithm. The operators specific to this problem, mutation and transposition, are used as the transition operators. The method incorporates time-dependent start-up costs, demand and reserve constraints, minimum up and down time constraints and unit power generation limits. There are different definitions of the objective function for the feasible and infeasible solutions. Test results showed an improvement in effectiveness compared to results obtained from simulated annealing with a static schedule, genetic algorithm and other techniques.
    Electric Power Systems Research 04/2010; 80(4-80):465-472. DOI:10.1016/j.epsr.2009.10.019 · 1.75 Impact Factor
Show more