A GA-based multiple simulated annealing

As demonstrated in Chap. 3, different evolutionary algorithms, including genetic algorithm (GA), simulated annealing (SA) algorithm, hybrid GASA algorithm, particle swarm optimization (PSO) algorithm, continuous ant colony optimization (CACO) algorithm, artificial bee colony (ABC) algorithm, and immune algorithm (IA), are employed to determine suitable for parameter combination of an SVR-based electric load forecasting model. These forecasting results indicate that almost all SVR-based models with different evolutionary algorithms are superior to other competitive forecasting models (including ARIMA, HW, GRNN, and BPNN models); however, these algorithms almost lack knowledge memory or storage mechanisms which would be neither time-consuming nor inefficient in searching the suitable parameters, that is, premature convergence (being trapped in local optimum). For example, for SVRGA model, in GA processing, new individuals are generated by the following operators, selection, crossover, and mutation. For all types of objective functions, the generation begins with a binary coding for the parameter set. Based on this special binary coding process, GA is able to solve some specified problems which are not easily to be solved by traditional algorithms. GA can empirically provide a few best fitted offsprings from the whole population; however, after some generations, due to low diversity of the population, it might lead to a premature convergence [1]. For SVRSA model, SA algorithm is a generic probabilistic search technique that simulates the material physical process of heating and controlled cooling. Each step of SA attempts to replace the current state by a random move. The new state may then be accepted with a probability that depends both on the difference between the corresponding function values and also on a global parameter, temperature. Thus, SA has some institution to reach more ideal solutions. However, SA algorithm requires the subtle and skillful adjustment in the annealing schedule; therefore, the settings of the size of the temperature steps during annealing, the temperature range, the number of restarts, and the redirection of the search will be taken into account carefully [1]; in addition, its Monte Carlo scheme and lack of knowledge memory mechanism will also lead to time-consuming and inefficient searching in annealing process.

A combined strategy of an improved simulated annealing (SA) algorithm and genetic algorithm is presented, with the goal of reducing the computational expenses. The improvements made on the SA algorithm include two parts, i.e., the adaptive regulating for the step vector, and the dynamic testing for the equilibrium of the Metropolis process. The proposed strategy has both the advantage of SA algorithm, the ability to avoid being trapped in a local optimum, and that of genetic algorithm, the ability to use the information about the searched states for the next iteration. A practical application on geometry optimization of pole shoes in large salient pole synchronous generators is effectively implemented using the strategy. The numerical results show that the number of iterations used by executing the combined strategy are only about 75% of those by executing basic SA algorithm.

Evolutionary algorithms, simulated annealing and tabu search: a comparative study

This paper explores the potential of quantum computing on a WCET(Worst-Case Execution Time (of a program).)-related combinatorial optimization problem applied to a set of several polynomial special cases. We consider the maximization problem of determining the most expensive path in a control flow graph. In these graphs, vertices represent blocks of code whose execution times are fixed and known in advance. We port the considered optimization problem to the quantum framework by expressing it as a QUBO. We then experimentally compare the performances in solving the problem of classic Simulated Annealing (SA), Quantum Annealing (QA), and Quantum Approximate Optimization Algorithm (QAOA). Our experiments suggest that QA represents a fast equivalent of simulated annealing. Indeed, we measured the approximation ratio on the results of QA and SA, showing that their performances are comparable, at least on our set of simplified problems.KeywordsWCETsQuantum computingQUBOCombinatorial optimizationQuantum annealingQAOA

SUMMARY Many interesting inverse problems in geophysics are non-linear and multimodal. Parametrization of these problems leads to an objective function, or measure of agreement between data and model predictions, that has a complex topography with many local minima. Optimization algorithms that rely on local gradients in the objective function or that search the model space locally may become trapped in these local minima. By combining simulated annealing with the downhill simplex method, a hybrid global search algorithm is presented in this paper for non-linear, multimodal, inverse problems. The hybrid algorithm shares the advantages of both local search methods that perform well if the local model is suitable, and global methods that are able to explore efficiently the full model space. The hybrid algorithm also utilizes a larger and more complex memory to store information on the objective function than simulated annealing algorithms. The effectiveness of this new scheme is evaluated in three problems: minimization of the multidimensional Rosenbrock function, non-linear, 1 -D, acoustic waveform inversion, and residual statics. The performance of the hybrid algorithm is compared with simulated annealing and genetic algorithms and is shown to converge more rapidly and to have a higher success rate of locating the global minimum for the cases investigated.

Evolutionary algorithms (EAs) have been widely used to search for optimal strategies for the planning and management of water resources systems, particularly reservoir operation. This study provides a comprehensive diagnostic assessment of state of the art of the non-animal-inspired EA applications to reservoir optimization. This type of EAs does not mimic biologic traits and group strategies of animal (wild) species. A search of pertinent papers was applied to the journal citation reports (JCRs). A bibliometric survey identified 14 pertinent non-animal-inspired EAs, such as the genetic algorithm (GA), simulated annealing (SA), and differential evolution (DE) algorithms, most of which have a number of modified versions. The characteristics of non-animal-inspired EAs and their modified versions were discussed to identify the difference between EAs and how each EA was improved. Additionally, the type of application of non-animal-inspired EAs to different case studies was investigated, and comparisons were made between the performance of the applied EAs in the studied literature. The survey revealed that the GA is the most frequently applied algorithm, followed by the DE algorithm. Non-animal-inspired EAs are superior to the classical methods of reservoir optimization (e.g., the non-linear programming and dynamic programming) due to faster convergence, diverse solution space, and efficient objective function evaluation. Several non-animal-inspired EAs of recent vintage have been shown to outperform the classic GA, which was the first evolutionary algorithm applied to reservoir operation.

In this article, three evolutionary search algorithms: particle swarm optimization (PSO), simulated annealing (SA) and genetic algorithms (GA), have been employed to determine the optimal parameter values of the fractional-order (FO)-PI controllers implemented in the dual active bridge-based (DAB) DC microgrid. The optimum strategy to obtain the parameters of these FO-PI controllers is still a major challenge for many power systems applications. The FO-PI controllers implemented in the DAB are used to control the DC link voltage to the desired value and limit the current flowing through the converter. Accordingly, the investigated control system has six parameters to be tuned simultaneously; Kp1, Ki1, λ1 for FO-PI voltage controller and Kp2, Ki2, λ2 for FO-PI current controller. Crucially, this tuning optimization process has been developed to enhance the voltage stability of a DC microgrid. By observing the frequency-domain analysis of the closed-loop and the results of the subsequent time-domain simulations, it has been demonstrated that the evolutionary algorithms have provided optimal controller gains, which ensures the voltage stability of the DC microgrid. The main contribution of the article can be considered in the successful application of evolutionary search algorithms to tune the parameters of FO-based dual loop controllers of a DC microgrid scheme whose power conditioner is a DAB topology.

Supervised Neural Network (NN) learning is a process in which input patterns and known targets are presented to a NN while it learns to recognize (classify, map, fit, etc.) them as desired. The learning is mathematically defined as an optimisation problem, i.e., an error function representing the differences between the desired and actual output, is being minimized (Bishop, 1995; Haykin, 1999). Because the most popular supervised learning techniques are gradient based (Backpropagation BP), they suffer from the so-called Local Minima Problem (Bishop, 1995). This has motivated the employment of Global Optimisation (GO) methods for the supervised NN learning. Stochastic and heuristic GO approaches including Evolutionary Algorithms (EA) demonstrated promising performance over the last decades (Smagt, 1994; Sexton et al., 1998; Jordanov & Georgieva, 2007; etc.). EA appeared more powerful than BP and its modifications (Sexton et al., 1998; Alba & Chicone 2004), but hybrid methods that combine the advantages of one or more GO techniques and local searches were proven to be even better (Yao, 1999; Rocha et al., 2003; Alba & Chicano, 2004; Ludemir et al., 2006). Hybrid methods were promoted over local searches and simple population based techniques in Alba & Chicone (2004). The authors compared five methods: two BP implementations (gradient descent and Levenberg-Marquardt), Genetic Algorithms (GA), and two hybrid methods, combining GA with different local methods. The methods were used for NN learning applied to problems arising in medicine. Ludemir et al. (2006) optimized simultaneously NN weights and topology with a hybrid method combining Simulated Annealing (SA), Tabu Search (TS) and BP. A set of new solutions was generated on each iteration by TS rules, but the best solution was only accepted according to the probability distribution as in conventional SA. Meanwhile, the topology of the NN was also optimized and the best solution was kept. Finally, BP was used to train the best NN topology found in the previous stages. The new methodology compared favorably with SA and TS on four classification and one prediction problems. Plaginakos et al. (2001) performed several experiments to evaluate various training methods – six Differential Evolution (DE) implementations (with different mutation operators), BP, BPD (BP with deflection), SA, hybridization of BP and SA (BPSA), and GA. They reported O pe n A cc es s D at ab as e w w w .in te ch w eb .o rg

Neural networks and fuzzy systems are two soft‐computing paradigms for system modelling. Adapting a neural or fuzzy system requires to solve two optimization problems: structural optimization and parametric optimization. Structural optimization is a discrete optimization problem which is very hard to solve using conventional optimization techniques. Parametric optimization can be solved using conventional optimization techniques, but the solution may be easily trapped at a bad local optimum. Evolutionary computation is a general‐purpose stochastic global optimization approach under the universally accepted neo‐Darwinian paradigm, which is a combination of the classical Darwinian evolutionary theory, the selectionism of Weismann, and the genetics of Mendel. Evolutionary algorithms are a major approach to adaptation and optimization. In this paper, we first introduce evolutionary algorithms with emphasis on genetic algorithms and evolutionary strategies. Other evolutionary algorithms such as genetic programming, evolutionary programming, particle swarm optimization, immune algorithm, and ant colony optimization are also described. Some topics pertaining to evolutionary algorithms are also discussed, and a comparison between evolutionary algorithms and simulated annealing is made. Finally, the application of EAs to the learning of neural networks as well as to the structural and parametric adaptations of fuzzy systems is also detailed.

(Hybrid) metaheuristics such as simulated annealing, genetic algorithms, or extremal optimization play a most prominent role in global optimization. The performance of these algorithms and their respective sampling behavior during the search process are themselves interesting problems. Here, we show that a combination of two approaches – namely Energy Landscape Paving (ELP) and Stochastic Tunneling (STUN) – can overcome known problems of other Metropolis-sampling-based procedures. We show on grounds of non-equilibrium statistical mechanics and empirical evidence on the synergistic advantages of this combined approach and discuss simulations for a complex optimization problem.

Summary The Simulated Annealing (SA) algorithm has been widely used in geophysical data processing. However, the seri al SA algorithm is limited by low computing efficiency. In this paper, the annealing schedule has been improved in the SA algorithm, and a constrained inversion of magnetotelluric (MT) data using the parallel SA algorithm has been applied. The test of synthetic data shows that the improved Very Fast Simulated Annealing (VFSA) method is significantly better than the traditional method. Additionally, the computing efficiency has been improved using the parallel SA inversion algorithm. This method has also been applied in MT data processing for geothermal exploration and good geological results have been achieved.

This paper proposes a new method for a modified particle swarm optimization algorithm (MPSO) combined with a simulated annealing algorithm (SA). MPSO is known as an efficient approach with a high performance of solving optimization problems in many research fields. It is a population intelligence algorithm inspired by social behavior simulations of bird flocking. Considerable research work on classical method PSO (Particle Swarm Optimization) has been done to improve the performance of this method. Therefore, the proposed hybrid optimization algorithms MPSO- SA use the combination of MPSO and simulated annealing SA. This method has the advantage to provide best results comparing with all heuristics methods PSO and SA. In this matter, a benchmark of eighteen well-known functions is given. These functions present different situations of finding the global minimum with gradual difficulties. Numerical results presented, in this paper, show the robustness of the MPSO-SA algorithm. Numerical comparisons with these three algorithms: Simulated Annealing, Modified Particle swarm optimization and MPSO-SA prove that the hybrid algorithm offers best results.

Novel computing paradigms for parameter estimation in Hammerstein controlled auto regressive auto regressive moving average systems

This paper investigates the reduction of side lobe level in antenna arrays. Reduction of side lobe level in antenna arrays has some limitations including fixed width of the beam. We have modeled the side lobe level reduction as an optimization problem using simulated annealing technique for side lobe level reduction of a specific beam width. The advantage of this method compared with other methods is that it can get out of local minimums and converge to the optimized answer. Efficiency of simulated annealing algorithm in pattern extraction of desired circular antenna, which is used frequently in modern telecommunication and radar systems, is investigated and the results are compared with that of genetic and evolutionary algorithms. Key words: Simulated annealing, antenna array, circular array, non-uniform antenna array, side lobe level.

Stochastic global search algorithms such as genetic algorithms are used to attack difficult combinatorial optimization problems. However, genetic algorithms suffer from the lack of a convergence proof. This means that it is difficult to establish reliable algorithm braking criteria without extensive a priori knowledge of the solution space. The hybrid genetic algorithm presented here combines a genetic algorithm with simulated annealing in order to overcome the algorithm convergence problem. The genetic algorithm runs inside the simulated annealing algorithm and provides convergence via a Boltzmann cooling process. The hybrid algorithm was used successfully to solve a classical 30-city traveling salesman problem; it consistently outperformed both a conventional genetic algorithm and a conventional simulated annealing algorithm.