Anastasios G. Bakirtzis

A genetic algorithm solution to the unit commitment problem

This paper presents a genetic algorithm (GA) solution to the unit commitment problem. GAs are general purpose optimization techniques based on principles inspired from the biological evolution using metaphors of mechanisms such as natural selection, genetic recombination and survival of the fittest. A simple GA algorithm implementation using the standard crossover and mutation operators could locate near optimal solutions but in most cases failed to converge to the optimal solution. However, using the varying quality function technique and adding problem specific operators, satisfactory solutions to the unit commitment problem were obtained. Test results for power systems of up to 100 units and comparisons with results obtained using Lagrangian relaxation and dynamic programming are also reported.

A solution to the unit-commitment problem using integer-coded genetic algorithm

This paper presents a new solution to the thermal unit-commitment (UC) problem based on an integer-coded genetic algorithm (GA). The GA chromosome consists of a sequence of alternating sign integer numbers representing the sequence of operation/reservation times of the generating units. The proposed coding achieves significant chromosome size reduction compared to the usual binary coding. As a result, algorithm robustness and execution time are improved. In addition, generating unit minimum up and minimum downtime constraints are directly coded in the chromosome, thus avoiding the use of many penalty functions that usually distort the search space. Test results with systems of up to 100 units and 24-h scheduling horizon are presented.

A neural network short term load forecasting model for the Greek power system

This paper presents the development of an artificial neural network (ANN) based short-term load forecasting model for the Energy Control Center of the Greek Public Power Corporation (PPC). The model can forecast daily load profiles with a lead time of one to seven days. Attention was paid for the accurate modeling of holidays. Experiences gained during the development of the model regarding the selection of the input variables, the ANN structure, and the training data set are described in the paper. The results indicate that the load forecasting model developed provides accurate forecasts.

Short term load forecasting using fuzzy neural networks

This paper presents the development of a fuzzy system for short term load forecasting. The fuzzy system has the network structure and the training procedure of a neural network and is called a fuzzy neural network (FNN). An FNN initially creates a rule base from existing historical load data. The parameters of the rule base are then tuned through a training process, so that the output of the FNN adequately matches the available historical load data. Once trained, the FNN can be used to forecast future loads. Test results show that the FNN can forecast future loads with an accuracy comparable to that of neural networks, while its training is much faster than that of neural networks. >

A decentralized solution to the DC-OPF of interconnected power systems

This paper presents a new method for the decentralized solution of the DC optimal power flow (OPF) problem in large interconnected power systems. The method decomposes the overall OPF problem of a multiarea system into independent OPF subproblems, one for each area. The solutions of the OPF subproblems of the different areas are coordinated through a pricing mechanism until they converge to the global OPF solution. The prices used for the coordination of the subproblem solutions are the prices of electricity exchanges between adjacent areas. Test results from the application of the method to the three-area RTS-96 and the Balkan power system are reported.

Network-constrained economic dispatch using real-coded genetic algorithm

A genetic algorithm (GA) solution to the network-constrained economic dispatch problem is presented. A real-coded GA has been implemented to minimize the dispatch cost while satisfying generating unit and branch power flow limits. A binary-coded GA was also developed to provide a means of comparison. GA solutions do not impose any convexity restrictions on the dispatch problem. The proposed method was applied on the electrical grid of Crete Island with satisfactory results. Various tests with both convex and nonconvex unit cost functions demonstrate that the proposed GA locates the optimum solution, while it is more efficient than the binary-coded GA.

A novel approach to short-term load forecasting using fuzzy neural networks

An efficient modeling technique based on the fuzzy curve notion is developed in this paper to generate fuzzy models for short-term load forecasting. The suggested forecasting approach proceeds on the following steps: (a) prediction of the load curve extremals (peak and valley loads) using separate fuzzy models; (b) formulation of the representative day based on historical load data; and (c) mapping of the representative day load curve to the forecasted peak values to obtain the predicted day load curves. Very good prediction performance is attained as shown in the simulation results which verify the effectiveness of the modeling technique.

Optimal Bidding Strategy for Electric Vehicle Aggregators in Electricity Markets

This paper determines the optimal bidding strategy of an electric vehicle (EV) aggregator participating in day-ahead energy and regulation markets using stochastic optimization. Key sources of uncertainty affecting the bidding strategy are identified and incorporated in the stochastic optimization model. The aggregator portfolio optimization model should include inevitable deviations between day-ahead cleared bids and actual real-time energy purchases as well as uncertainty for the energy content of regulation signals in order to ensure profit maximization and reliable reserve provision. Energy deviations are characterized as “uninstructed” or “instructed” depending on whether or not the responsibility resides with the aggregator. Price deviations and statistical characteristics of regulation signals are also investigated. Finally, a new battery model is proposed for better approximation of the battery charging characteristic. Test results with an EV aggregator representing one thousand EVs are presented and discussed.

A genetic algorithm solution approach to the hydrothermal coordination problem

In this paper, a genetic algorithm solution to the hydrothermal coordination problem is presented. The generation scheduling of the hydro production system is formulated as a mixed-integer, nonlinear optimization problem and solved with an enhanced genetic algorithm featuring a set of problem-specific genetic operators. The thermal subproblem is solved by means of a priority list method, incorporating the majority of thermal unit constraints. The results of the application of the proposed solution approach to the operation scheduling of the Greek Power System, comprising 13 hydroplants and 28 thermal units, demonstrate the effectiveness of the proposed algorithm.

Design of a stand alone system with renewable energy sources using trade off methods

The authors present an application of recent theoretical advances in multiobjective planning under uncertainty, in the design of a stand-alone system with renewable energy sources. The system under design consists of a wind energy plant, a solar plant, and an storage battery. Time series data on wind, insolation, and load for the site of interest are assumed to be available. The developed design methodology systematically selects the size of the various components of the system so as to give a robust design, i.e. a design that is a reasonable compromise between the conflicting design objectives under most foreseeable conditions. >