Forecasting Energy Consumption Using a Novel Hybrid Dipper Throated Optimization and Stochastic Fractal Search Algorithm

The accurate prediction of energy consumption has effective role in decision making and risk management for individuals and governments.Meanwhile,the accurate prediction can be realized using the recent advances in machine learning and predictive models.This research proposes a novel approach for energy consumption forecasting based on a new optimization algorithm and a new forecasting model consisting of a set of long short-term memory(LSTM)units.The proposed optimization algorithm is used to optimize the parameters of the LSTM-based model to boost its forecasting accuracy.This optimization algorithm is based on the recently emerged dipper-throated optimization(DTO)and stochastic fractal search(SFS)algo-rithm and is referred to as dynamic DTOSFS.To prove the effectiveness and superiority of the proposed approach,five standard benchmark algorithms,namely,stochastic fractal search(SFS),dipper throated optimization(DTO),whale optimization algorithm(WOA),particle swarm optimization(PSO),and grey wolf optimization(GWO),are used to optimize the parameters of the LSTM-based model,and the results are compared with that of the proposed approach.Experimental results show that the proposed DDTOSFS+LSTM can accurately forecast the energy consumption with root mean square error RMSE of 0.00013,which is the best among the recorded results of the other methods.In addition,statistical experiments are conducted to prove the statistical difference of the proposed model.The results of these tests confirmed the expected outcomes.

Deep Neural Network Architecture Search via Decomposition-Based Multi-Objective Stochastic Fractal Search

Deep neural networks often outperform classical machine learning algorithms in solving real-world problems.However,designing better networks usually requires domain expertise and consumes significant time and com-puting resources.Moreover,when the task changes,the original network architecture becomes outdated and requires redesigning.Thus,Neural Architecture Search(NAS)has gained attention as an effective approach to automatically generate optimal network architectures.Most NAS methods mainly focus on achieving high performance while ignoring architectural complexity.A myriad of research has revealed that network performance and structural complexity are often positively correlated.Nevertheless,complex network structures will bring enormous computing resources.To cope with this,we formulate the neural architecture search task as a multi-objective optimization problem,where an optimal architecture is learned by minimizing the classification error rate and the number of network parameters simultaneously.And then a decomposition-based multi-objective stochastic fractal search method is proposed to solve it.In view of the discrete property of the NAS problem,we discretize the stochastic fractal search step size so that the network architecture can be optimized more effectively.Additionally,two distinct update methods are employed in step size update stage to enhance the global and local search abilities adaptively.Furthermore,an information exchange mechanism between architectures is raised to accelerate the convergence process and improve the efficiency of the algorithm.Experimental studies show that the proposed algorithm has competitive performance comparable to many existing manual and automatic deep neural network generation approaches,which achieved a parameter-less and high-precision architecture with low-cost on each of the six benchmark datasets.

Stochastic focusing search:a novel optimization algorithm for real-parameter optimization

A novel optimization algorithm called stochastic focusing search （SFS） for the real-parameter optimization is proposed. The new algorithm is a swarm intelligence algorithm, which is based on simulating the act of human randomized searching, and the human searching behaviors. The algorithm＇s performance is studied using a challenging set of typically complex functions with comparison of differential evolution （DE） and three modified particle swarm optimization （PSO） algorithms, and the simulation results show that SFS is competitive to solve most parts of the benchmark problems and will become a promising candidate of search algorithms especially when the existing algorithms have some difficulties in solving certain problems.

A hybrid stochastic fractal search and pattern search technique based cascade PI-PD controller for automatic generation control of multi-source power systems in presence of plug in electric vehicles

A hybrid Stochastic Fractal Search plus Pattern Search （hSFS-PS） based cascade PI-PD controller is suggested in this paper for Automatic Generation Control （AGC） of thermal, hydro and gas power unit based power systems in presence of Plug in Electric Vehicles （PEV）. Firstly, a single area multi-source power system consisting of thermal hydro and gas power plants is considered and parameters of Integral （I） controller is optimized by Stochastic FractaI Search （SFS） algorithm. The superiority of SFS algorithm over some recently proposed approaches such as optimal control, differential evolution and teaching learning based optimization techniques is demonstrated by comparing simulation results for the identical power system. To improve the system performance further, Pattern Search （PS） is subsequently employed. The study is further extended for different controllers like PI, PID, and cascaded PI-PD controller and the superiority of cascade PI-PD controller over conventional controllers is demonstrated. Then, cascade PI- PD controller parameters of AGC searched using the proposed hSFS-PS algorithm in presence of plug in electric vehicles. The study is also extended to an interconnected power system. It is seen from the comparative analysis that hSFS-PS tuned PI-PD controller in single and multi-area with multi sources improves the system frequency stability in complicated situations. Lastly, a three area interconnected system with PEVs with dissimilar cascade PI-PD controller in each area is considered and proposed hSFS- PS algorithm is used to tune the controller parameters in presence of nonlinearities like rate constraint of units, dead zone of governor and communication delay.

Reactive Search Optimization;Application to Multiobjective Optimization Problems

During the last few years we have witnessed impressive developments in the area of stochastic local search techniques for intelligent optimization and Reactive Search Optimization. In order to handle the complexity, in the framework of stochastic local search optimization, learning and optimization has been deeply interconnected through interaction with the decision maker via the visualization approach of the online graphs. Consequently a number of complex optimization problems, in particular multiobjective optimization problems, arising in widely different contexts have been effectively treated within the general framework of RSO. In solving real-life multiobjective optimization problems often most emphasis are spent on finding the complete Pareto-optimal set and less on decision-making. However the com-plete task of multiobjective optimization is considered as a combined task of optimization and decision-making. In this paper, we suggest an interactive procedure which will involve the decision-maker in the optimization process helping to choose a single solution at the end. Our proposed method works on the basis of Reactive Search Optimization (RSO) algorithms and available software architecture packages. The procedure is further compared with the excising novel method of Interactive Multiobjective Optimization and Decision-Making, using Evolutionary method (I-MODE). In order to evaluate the effectiveness of both methods the well-known study case of welded beam design problem is reconsidered.

Solving constrained portfolio optimization model using stochastic fractal search approach

Purpose-Optimum utilization of investments has always been considered one of the most crucial aspects of capital markets.Investment into various securities is the subject of portfolio optimization intent to maximize return at minimum risk.In this series,a population-based evolutionary approach,stochastic fractal search(SFS),is derived from the natural growth phenomenon.This study aims to develop portfolio selection model using SFS approach to construct an efficient portfolio by optimizing the Sharpe ratio with risk budgeting constraints.Design/methodology/approach-This paper proposes a constrained portfolio optimization model using the SFS approach with risk-budgeting constraints.SFS is an evolutionary method inspired by the natural growth process which has been modeled using the fractal theory.Experimental analysis has been conducted to determine the effectiveness of the proposed model by making comparisons with state-of-the-art from domain such as genetic algorithm,particle swarm optimization,simulated annealing and differential evolution.The real datasets of the Indian stock exchanges and datasets of global stock exchanges such as Nikkei 225,DAX 100,FTSE 100,Hang Seng31 and S&P 100 have been taken in the study.Findings-The study confirms the better performance of the SFS model among its peers.Also,statistical analysis has been done using SPSS 20 to confirm the hypothesis developed in the experimental analysis.Originality/value-In the recent past,researchers have already proposed a significant number of models to solve portfolio selection problems using the meta-heuristic approach.However,this is the first attempt to apply the SFS optimization approach to the problem.

Hybridized Artificial Neural Network for Automated Software Test Oracle

Software testing is the methodology of analyzing the nature of software to test if it works as anticipated so as to boost its reliability and quality.These two characteristics are very critical in the software applications of present times.When testers want to perform scenario evaluations,test oracles are generally employed in the third phase.Upon test case execution and test outcome generation,it is essential to validate the results so as to establish the software behavior’s correctness.By choosing a feasible technique for the test case optimization and prioritization as along with an appropriate assessment of the application,leads to a reduction in the fault detection work with minimal loss of information and would also greatly reduce the cost for clearing up.A hybrid Particle Swarm Optimization(PSO)with Stochastic Diffusion Search(PSO-SDS)based Neural Network,and a hybrid Harmony Search with Stochastic Diffusion Search(HS-SDS)based Neural Network has been proposed in this work.Further to evaluate the performance,it is compared with PSO-SDS based artificial Neural Network(PSO-SDS ANN)and Artificial Neural Network(ANN).The Misclassification of correction output(MCO)of HS-SDS Neural Network is 6.37 for 5 iterations and is well suited for automated testing.

Enhanced self-adaptive evolutionary algorithm for numerical optimization

There are many population-based stochastic search algorithms for solving optimization problems. However, the universality and robustness of these algorithms are still unsatisfactory. This paper proposes an enhanced self-adaptiveevolutionary algorithm （ESEA） to overcome the demerits above. In the ESEA, four evolutionary operators are designed to enhance the evolutionary structure. Besides, the ESEA employs four effective search strategies under the framework of the self-adaptive learning. Four groups of the experiments are done to find out the most suitable parameter values for the ESEA. In order to verify the performance of the proposed algorithm, 26 state-of-the-art test functions are solved by the ESEA and its competitors. The experimental results demonstrate that the universality and robustness of the ESEA out-perform its competitors.

Electromagnetism-Like Mechanism Algorithm with New Charge Formula for Optimization

The electromagnetism-like(EM)algorithm is a meta-heuristic optimization algorithm,which uses a novel searching mechanism called attraction-repulsion between charged particles.It is worth pointing out that there are two potential problems in the calculation of particle charge by the original EM algorithm.One of the problems is that the information utilization rate of the population is not high,and the other problem is the decline of population diversity when the population size is much greater than the dimension of the problem.In contrast,it is more fully to exploit the useful search information based on the proposed new quadratic formula for charge calculation in this paper.Furthermore,the population size was introduced as a new multiplier term to improve the population diversity.In the end,numerical experiments were used to verify the performance of the proposed method,including a comparison with the original EM algorithm and other well-known methods such as artificial bee colony(ABC),and particle swarm optimization(PSO).The results showed the effectiveness of the proposed algorithm.

Optimal Combined Heat and Power Economic Dispatch Using Stochastic Fractal Search Algorithm

Combined heat and power(CHP)generation is a valuable scheme for concurrent generation of electrical and thermal energies.The interdependency of power and heat productions in CHP units introduces complications and non-convexities in their modeling and optimization.This paper uses the stochastic fractal search(SFS)optimization technique to treat the highly non-linear CHP economic dispatch(CHPED)problem,where the objective is to minimize the total operation cost of both power and heat from generation units while fulfilling several operation interdependent limits and constraints.The CHPED problem has bounded feasible operation regions and many local minima.The SFS,which is a recent metaheuristic global optimization solver,outranks many current reputable solvers.Handling constraints of the CHPED is achieved by employing external penalty parameters,which penalize infeasible solution during the iterative process.To confirm the strength of this algorithm,it has been tested on two different test systems that are regularly used.The obtained outcomes are compared with former outcomes achieved by many different methods reported in literature of CHPED.The results of this work affirm that the SFS algorithm can achieve improved near-global solution and compare favorably with other commonly used global optimization techniques in terms of the quality of solution,handling of constraints and computation time.

Solving the Euclidean Steiner Minimum Tree Using Cellular Stochastic Diffusion Search Algorithm

The Euclidean Steiner minimum tree problem is a classical NP-hard combinatorial optimization problem.Because of the intrinsic characteristic of the hard computability,this problem cannot be solved accurately by efficient algorithms up to now.Due to the extensive applications in real world,it is quite important to find some heuristics for it.The stochastic diffusion search algorithm is a newly population-based algorithm whose operating mechanism is quite different from ordinary intelligent algorithms,so this algorithm has its own advantage in solving some optimization problems.This paper has carefully studied the stochastic diffusion search algorithm and designed a cellular automata stochastic diffusion search algorithm for the Euclidean Steiner minimum tree problem which has low time complexity.Practical results show that the proposed algorithm can find approving results in short time even for the large scale size,while exact algorithms need to cost several hours.