Differential Search Algorithm Research Articles

Parameter estimation by Differential Search Algorithm from horizontal loop electromagnetic (HLEM) data

We present an efficient inversion tool for parameter estimation from horizontal loop electromagnetic (HLEM) data using Differential Search Algorithm (DSA) which is a swarm-intelligence-based metaheuristic proposed recently. The depth, dip, and origin of a thin subsurface conductor causing the anomaly are the parameters estimated by the HLEM method commonly known as Slingram. The applicability of the developed scheme was firstly tested on two synthetically generated anomalies with and without noise content. Two control parameters affecting the convergence characteristic to the solution of the algorithm were tuned for the so-called anomalies including one and two conductive bodies, respectively. Tuned control parameters yielded more successful statistical results compared to widely used parameter couples in DSA applications. Two field anomalies measured over a dipping graphitic shale from Northern Australia were then considered, and the algorithm provided the depth estimations being in good agreement with those of previous studies and drilling information. Furthermore, the efficiency and reliability of the results obtained were investigated via probability density function. Considering the results obtained, we can conclude that DSA characterized by the simple algorithmic structure is an efficient and promising metaheuristic for the other relatively low-dimensional geophysical inverse problems. Finally, the researchers after being familiar with the content of developed scheme displaying an easy to use and flexible characteristic can easily modify and expand it for their scientific optimization problems.

Maximum Power Point Tracking in Solar Power Systems by Using Differential Evolution Methods with Embedded Systems

In this paper, one of the most important problems, Maximum Power Point Tracking (MPPT), in renewable solar power is studied and analyzed. In order to obtain the maximum power point in solar cells and panels the voltage and current should be maximized, simultaneously. Thus, the easiest way to achieve the maximum power point is tracking the solar energy, daylight, by measuring the light intensity in a solar cell or panel coaxially. In this work, the MPPT is achieved by optimizing the light intensity vector on a solar panel after measuring the daylight physically with the help of newly designed embedded system, and processing the real world values by using Differential Search Algorithm which is a new and improved method based on differential evolutionary principles.

Optimized Deep Learning for EEG Big Data and Seizure Prediction BCI via Internet of Things

A brain-computer interface (BCI) for seizure prediction provides a means of controlling epilepsy in medically refractory patients whose site of epileptogenicity cannot be resected but yet can be defined sufficiently to be selectively influenced by strategically implanted electrodes. Challenges remain in offering real-time solutions with such technology because of the immediacy of electrographic ictal behavior. The nonstationary nature of electroencephalographic (EEG) and electrocorticographic (ECoG) signals results in wide variation of both normal and ictal patterns among patients. The use of manually extracted features in a prediction task is impractical and the large amount of data generated even among a limited set of electrode contacts will create significant processing delays. Big data in such circumstances not only must allow for safe storage but provide high computational resources for recognition, capture and real-time processing of the preictal period in order to execute the timely abrogation of the ictal event. By leveraging the potential of cloud computing and deep learning, we develop and deploy BCI seizure prediction and localization from scalp EEG and ECoG big data. First, a new method for epileptic seizure prediction and localization of the seizure focus is presented. Second, an extended optimization approach on existing deep-learning structures, Stacked Auto-encoder and Convolutional Neural Network (CNN), is proposed based on principle component analysis (PCA), independent component analysis (ICA), and Differential Search Algorithm (DSA). Third, a cloud-computing solution (i.e., Internet of Things (IoT)), is developed to define the proposed structures for real-time processing, automatic computing and storage of big data. The ECoG clinical datasets on 11 patients illustrate the superiority of the proposed patient-specific BCI as an alternative to current methodology to offer support for patients with intractable focal epilepsy.

Improved differential search algorithm based dynamic resource allocation approach for cloud application

The performance of a service-based system (SBS) in a cloud environment may not satisfy service-level agreement (SLA) constraints when the system load changes. To improve the profits of resource providers and satisfy the global SLA, it is necessary to dynamically allocate proper resource for SBS based on the forecasted system load. By analyzing the complex workflow of the SBS, this paper proposes improved differential search algorithm-based dynamic resource allocation approach which adopts an active mechanism to respond to the change of system load so as to ensure the timely response to change. The dynamic resource allocation model based on costs optimization and SLA constraint is then proposed. The improved differential search algorithm is designed to solve the dynamic resource allocation model. This paper proposes a load forecasting approach based on deep belief networks (DBNs) in order to accurately forecast the load to support dynamic resource allocation. Experimental results show that the approach performs well in terms of the quality of the solution compared with other related approaches.

Influence of randomization strategies and problem characteristics on the performance of Differential Search algorithm

In this work, the influence of different random number generators, problem dimensionality, and number of function evaluations on the optimization efficiency of Differential Search algorithm is presented in detail. Two types of random number generators were taken into account: discrete and continuous. Different combinations between the dimensionality property and the number of function evaluation setting were tested on: i) a set of benchmark functions from the CEC 2013 special session on real parameter optimization; and ii) 2 chemical engineering problems (optimal operation of an alkylation unit and heat exchanger network design). Also, a comparison with other optimizers was performed. It was found that, in similar conditions, the performance of the algorithm (in terms of the best solutions) varies substantially depending on the distribution used. In case of the benchmark problems, the best solutions were obtained for Binomial and Weibull distribution. For the separable functions is was observed that, indifferent of the distribution used, the algorithm was not able to find acceptable solution within the constraint represented by the number of function evaluations. In the case of the alkylation problem the best solutions were obtained by the Weibull distribution, the performance of the Differential Search algorithm being comparable to other optimizers such as Differential Evolution. In the case of the heat exchanger, three different distribution provided near optimal solutions (Binomial, ChiSquare and Weibull).

Scalable computational framework using intelligent optimization: Microgrids dispatch and electricity market joint simulation

Worldwide microgrid capacity is expected to reach 7 GW and a market value of $35 billion dollars in the next few years. The decentralization of the generation dispatch role and different ownership models concerning microgrids, will contribute to increase the complexity of the future power systems. Analyzing new policies and strategies as well as evaluating those impacts is only possible with the use of sophisticated simulation tools. This paper presents a scalable computational simulation to address microgrid dispatch and the impact in the electricity market. Computational intelligence techniques are integrated to improve the effectiveness of the simulation tool. These techniques include CPLEX; differential search algorithm and quantum particle swarm optimization. Each microgrid player is able to solve a day-ahead scheduling problem and submit bids to the electricity market agent (spot market), which calculates the market clearing price. The developed case study with a large number of players totaling about 150,000 consumers suggest the relevance of the developed computational framework.

A Pareto optimal approach for allocation of distributed generators in radial distribution systems using improved differential search algorithm

Optimal allocation of distributed generators (DG) in the radial distribution system plays a significant role in minimizing real power losses, network operational cost and improved voltage profile. The aim of the work is to select optimal sizes and locations for DGs in radial distribution systems (RDS) to minimize losses, improve voltage profile and minimize operating cost. Improved Differential Search Algorithm (IDSA) is used to solve the optimization problem via Pareto optimal approach by considering technical and financial benefits of DGs as objectives. Proposed approach is implemented on standard 33-bus and 69-bus RDS and the results are compared with the existing methods. The proposed approach is capable of producing high quality solution with satisfied constraints.

The Binary Differential Search Algorithm Approach for Solving Uncapacitated Facility Location Problems

Recently, many Computational-Intelligence algorithms have been proposed for solving continuous problem. The Differential Search Algorithm (DSA), a computational-intelligence based algorithm inspired by the migration movements of superorganisms, is developed to solve continuous problems. However, DSA proposed for solving problems with continuous search space proposed for solving should be modified for solving binary structured problems. When the DSA is intended for use in binary problems, continuous variables need to be converted into binary format due to solution space structure of this type of problem. In this study, the DSA is modified to solve binary optimization problems by using a conversion approach from continuous values to binary values. The new algorithm has been designated as the binary DSA or BDSA for short. First, when finding donors with the BDSA, four search methods (Bijective, Surjective, Elitist1 and Elitist2) with different iteration numbers are used and tested on 15 UFLP benchmark problems. The Elitist2 approach, which provides the best solution of the four methods, is used in the BDSA, and the results are compared with Continuous Particle Swarm Optimization (CPSO), Continuous Artificial Bee Colony (ABCbin), Improved Binary Particle Swarm Optimization (IBPSO), Binary Artificial Bee Colony (binABC) and Discrete Artificial Bee Colony (DisABC) algorithms using UFLP benchmark problems. Results from the tests and comparisons show that the BDSA is fast, effective and robust for binary optimization.

Using differential search algorithm for solving optimal frequency regulation problem in interconnected power system

In order to improve the frequency stability and control in an interconnected power system including various power generating units, the automatic generation control (AGC) needs to be more robust and efficient. On the other hand, the difficulties in AGC are not only to design a robust controller but it also to optimise its parameters effectively for a robust optimal solution. In this paper, an application of a new efficient optimisation method called the differential search algorithm (DSA) was proposed to solve the AGC problem. The proposed approach was applied to reach the proportional-integral-derivative (PID) controller parameters. This latter was used to maintain the frequency at nominal value using the integral time multiplied by absolute error (ITAE) as fitness function. To show the robustness of the proposed strategy, a four area interconnected electrical network was investigated for the simulation. The obtained DSA results were compared to other approaches available in literature. The simulation results of this research show that DSA strategy is able to solve AGC problem and achieve less frequency and tie-line power flow deviations than those determined by other methods used in this paper.

Using differential search algorithm for solving optimal frequency regulation problem in interconnected power system

Using differential search algorithm for solving optimal frequency regulation problem in interconnected power system

EEG rhythm/channel selection for fuzzy rule-based alertness state characterization

The aim of the paper is to automatically select the optimal EEG rhythm/channel combinations capable of classifying human alertness states. Four alertness states were considered, namely ‘engaged’, ‘calm’, ‘drowsy’ and ‘asleep’. The features used in the automatic selection are the energies associated with the conventional rhythms, \(\delta , \theta , \alpha , \beta\) and \(\gamma\), extracted from overlapping windows of the different EEG channels. The selection process consists of two stages. In the first stage, the optimal brain regions, represented by sets of EEG channels, are selected using a simple search technique based on support vector machine (SVM), extreme learning machine (ELM) and LDA classifiers. In the second stage, a fuzzy rule-based alertness classification system (FRBACS) is used to identify, from the previously selected EEG channels, the optimal features and their supports. The IF–THEN rules used in FRBACS are constructed using a novel differential evolution-based search algorithm particularly designed for this task. Each alertness state is represented by a set of IF–THEN rules whose antecedent parts contain EEG rhythm/channel combination. The selected spatio-frequency features were found to be good indicators of the different alertness states, as judged by the classification performance of the FRBACS that was found to be comparable to those of the SVM, ELM and LDA classifiers. Moreover, the proposed classification system has the advantage of revealing simple and easy to interpret decision rules associated with each of the alertness states.

Study of differential search algorithm based automatic generation control of an interconnected thermal-thermal system with governor dead-band

An attempt has been made to the effective application of a recently introduced, powerful optimization technique called differential search algorithm (DSA), for the first time to solve load frequency control (LFC) problem in power system. In this paper, initially, DSA optimized classical PI/PIDF controller is implemented to an identical two-area thermal-thermal power system and then the study is extended to two more realistic power systems which are widely used in the literature. To assess the usefulness of DSA, three enhanced competitive algorithms namely comprehensive learning particle swarm optimization (CLPSO), ensemble of mutation and crossover strategies and parameters in differential evolution (EPSDE), and success history based DE (SHADE) are studied in this paper. Moreover, the superiority of proposed DSA optimized PI/PID/PIDF controller is validated by an extensive comparative analysis with some recently published meta-heuristic algorithms such as firefly algorithm (FA), bacteria foraging optimization algorithm (BFOA), genetic algorithm (GA), craziness based particle swarm optimization (CRPSO), differential evolution (DE), teaching-learning based optimization (TLBO), particle swarm optimization (PSO), and quasi-oppositional harmony search algorithm (QOHSA). A case of robustness and sensitivity analysis has been performed for the concerned test system under parametric uncertainty and random load perturbation. Furthermore, to demonstrate the efficacy of proposed DSA, the system nonlinearities like reheater of the steam turbine and governor dead band are included in the system modeling. The extensive results presented in this article demonstrate that proposed DSA can effectively improve system dynamics and may be applied to real-time LFC problem.

Community detection from biological and social networks: A comparative analysis of metaheuristic algorithms

In order to analyze complex networks to find significant communities, several methods have been proposed in the literature. Modularity optimization is an interesting and valuable approach for detection of network communities in complex networks. Due to characteristics of the problem dealt with in this study, the exact solution methods consume much more time. Therefore, we propose six metaheuristic optimization algorithms, which each contain a modularity optimization approach. These algorithms are the original Bat Algorithm (BA), Gravitational Search Algorithm (GSA), modified Big Bang–Big Crunch algorithm (BB-BC), improved Bat Algorithm based on the Differential Evolutionary algorithm (BADE), effective Hyperheuristic Differential Search Algorithm (HDSA) and Scatter Search algorithm based on the Genetic Algorithm (SSGA). Four of these algorithms (HDSA, BADE, SSGA, BB-BC) contain new methods, whereas the remaining two algorithms (BA and GSA) use original methods. To clearly demonstrate the performance of the proposed algorithms when solving the problems, experimental studies were conducted using nine real-world complex networks − five of which are social networks and the rest of which are biological networks. The algorithms were compared in terms of statistical significance. According to the obtained test results, the HDSA proposed in this study is more efficient and competitive than the other algorithms that were tested.

Quasi-oppositional differential search algorithm applied to load frequency control

In this article, quasi-oppositional differential search algorithm (QODSA) is proposed for finding an optimal and effective solution for load frequency control (LFC) problem in the power system. Initially, original DSA is employed for fine-tuning of the secondary controller of LFC system and then, quasi-oppositional based learning (Q-OBL) mechanism is integrated into the original DSA to enhance the convergence speed and to find a better solution of LFC problem. To validate the effectiveness of proposed QODSA, four widely used interconnected power system networks are designed and analyzed. The superiority of the proposed method is established by an extensive comparative analysis with other existing evolutionary algorithm’s (EA) using transient analysis method. A critical investigation of simulation results reveals that the proposed QODSA gives simple and better solution compared to original DSA and other reported algorithms. To study the robustness of QODSA, two different random load patterns are projected and results confirm the robustness of the designed controllers. To add some degree of nonlinearity, generation rate constraint and governor dead band effects are considered and their consequence on the system dynamics has been examined. Finally, sensitivity analysis is performed with a wide variation of system parameters.

Optimal reactive-power dispatch using differential search algorithm

Optimal reactive-power dispatch (ORPD) is one of the most difficult optimization problems regarding to power-system operation which is heavily related to system stability. To overcome ORPD problem, in general, the total real-power loss is reduced by determining the power-system control parameters, such as generator voltages, tap ratios of tap-changer transformers, and compensated reactive power, optimally. In this paper, a simple and efficient heuristic search method based on the differential search algorithm (DSA) has been presented and used to solve the ORPD problem in power systems. The ORPD problem was overcome on the IEEE 30 bus and IEEE 57 bus test systems by achieving optimal solution sets of system control variables for the objective functions regarding to power-loss minimization, voltage-profile improvement, and voltage-stability enhancement. By comparing with the several optimization methods, the performance of DSA is tested and verified on the aforementioned power system. Optimization results of different cases and objective functions indicate the implementability of the proposed algorithm in terms of solving the ORPD problem as well as other single- and multi-objective optimization problems regarding to power systems.

An efficient approach for optimal multilevel thresholding selection for gray scale images based on improved differential search algorithm

Abstract Segmentation is one of the important steps for image analysis. Multilevel thresholding image segmentation was more popular in image segmentation. Otsu and Kapur based methods are most popular for multilevel threshold image segmentation. Many authors implemented evolutionary algorithms for the optimal multilevel threshold selection based on the above methods. In this paper, an efficient approach for multilevel image segmentation has been proposed and implemented based on novel evolutionary algorithm Improved Differential Search (IDS). The feasibility of proposed approach/algorithm has been tested on standard gray scale images. To check the effectiveness of the proposed approach/algorithm, all experimental results are analyzed quantitatively and qualitatively.

A Binary differential search algorithm for the 0–1 multidimensional knapsack problem

The multidimensional knapsack problem (MKP) is known to be NP-hard in operations research and it has a wide range of applications in engineering and management. In this study, we propose a binary differential search method to solve 0–1 MKPs where the stochastic search is guided by a Brownian motion-like random walk. Our proposed method comprises two main operations: discrete solution generation and feasible solution production. Discrete solutions are generated by integrating Brownian motion-like random search with an integer-rounding operation. However, the rounded discrete variables may violate the constraints. Thus, a feasible solution production strategy is used to maintain the feasibility of the rounded discrete variables. To demonstrate the efficiency of our proposed algorithm, we solved various 0–1 MKPs using our proposed algorithm as well as some existing meta-heuristic methods. The numerical results obtained demonstrated that our algorithm performs better than existing meta-heuristic methods. Furthermore, our algorithm has the capacity to solve large-scale 0–1 MKPs.

Sympathetic Trippings Blocking in Over Current Relay Coordination Algorithm during Steady State & Transient Network Topologies

Abstract In this paper an improved over current relay coordination protection technique is proposed. The proposed technique eliminates the sympathetic/nuisance tripping in an interconnected distribution system. Nuisance trippings are eliminated by incorporating the additional selectivity constraints in conventional over current relay coordination problem. Whenever the fault is cleared only from one end of the line in bidirectional fault feed lines, transient network configuration comes into existence. Transient network configuration causes the redistribution of fault in the distribution system and leads to further nuisance tripping of relays. This problem in this paper is solved by minimising the operating time gap between primary relays located at near end and far end of a faulty line to the best minimum possible value. The differential search algorithm is applied for optimization of highly non-linear over current relay coordination problem in this paper. The result presented in this paper shows that the proposed over current relay coordination technique is immune against the sympathetic/nuisance tripping and operating time difference between primary relays at near end and far end is also minimised within acceptable time margin successfully.

Elliptical Antenna Array Synthesis Using Backtracking Search Optimisation Algorithm

The design of the elliptical antenna arrays is relatively new research area in the antenna array community. Backtracking search optimisation algorithm (BSA) is employed for the synthesis of elliptical antenna arrays having different number of array elements. For this aim, BSA is used to calculate the optimum angular position and amplitude values of the array elements. BSA is a population-based iterative evolutionary algorithm. The remarkable properties of BSA are that it has a good optimisation performance, simple implementation structure, and few control parameters. The results of BSA are compared with those of self-adaptive differential evolution algorithm, firefly algorithm, biogeography based optimisation algorithm, and genetic algorithm. The results show that BSA can reach better solutions than the compared optimisation algorithms. Iterative performances of BSA are also compared with those of bacterial foraging algorithm and differential search algorithm.

Optimal allocation of remote control switches in radial distribution network for reliability improvement

Abstract This paper presents differential search algorithm in order to solve reliability optimization problem of radial distribution network. Remote control switches have been optimally allocated to improve reliability at a compromised cost. A multi-objective problem has been formulated and solved using differential search algorithm. The test systems considered in this paper are an 8 bus radial distribution network and a 33 bus radial distribution network. Simulation results obtained using differential search algorithm when applied to the test cases, have been compared with those obtained by particle swarm optimization. Differential search algorithm has been found to provide superior results as compared to particle swarm optimization.