Improved Differential Evolution Algorithm Research Articles

Medical image segmentation approach based on hybrid adaptive differential evolution and crayfish optimizer

Image segmentation plays a pivotal role in medical image analysis, particularly for accurately isolating tumors and lesions. Effective segmentation improves diagnostic precision and facilitates quantitative analysis, which is vital for medical professionals. However, traditional segmentation methods often struggle with multilevel thresholding due to the associated computational complexity. Therefore, determining the optimal threshold set is an NP-hard problem, highlighting the pressing need for efficient optimization strategies to overcome these challenges. This paper introduces a multi-threshold image segmentation (MTIS) method that integrates a hybrid approach combining Differential Evolution (DE) and the Crayfish Optimization Algorithm (COA), known as HADECO. Utilizing two-dimensional (2D) Kapur’s entropy and a 2D histogram, this method aims to enhance the efficiency and accuracy of subsequent image analysis and diagnosis. HADECO is a hybrid algorithm that combines DE and COA by exchanging information based on predefined rules, leveraging the strengths of both for superior optimization results. It employs Latin Hypercube Sampling (LHS) to generate a high-quality initial population. HADECO introduces an improved DE algorithm (IDE) with adaptive and dynamic adjustments to key DE parameters and new mutation strategies to enhance its search capability. In addition, it incorporates an adaptive COA (ACOA) with dynamic adjustments to the switching probability parameter, effectively balancing exploration and exploitation. To evaluate the effectiveness of HADECO, its performance is initially assessed using CEC’22 benchmark functions. HADECO is evaluated against several contemporary algorithms using the Wilcoxon signed rank test (WSRT) and the Friedman test (FT) to integrate the results. The findings highlight HADECO’s superior optimization abilities, demonstrated by its lowest average Friedman ranking of 1.08. Furthermore, the HADECO-based MTIS method is evaluated using MRI images for knee and CT scans for brain intracranial hemorrhage (ICH). Quantitative results in brain hemorrhage image segmentation show that the proposed method achieves a superior average peak signal-to-noise ratio (PSNR) and feature similarity index (FSIM) of 1.5 and 1.7 at the 6-level threshold. In knee image segmentation, it attains an average PSNR and FSIM of 1.3 and 1.2 at the 5-level threshold, demonstrating the method’s effectiveness in solving image segmentation problems.

Application of adaptive improved DE algorithm based on multi-angle search rotation crossover strategy in multi-circuit testing optimization

Abstract This study based on the standard differential evolution (DE) algorithm was carried out to address the issues of control parameter imprinting, mutation process, and crossover process in the standard DE algorithm as well as the issue of multidimensional circuit testing optimization. A rotation control vector was introduced to expand the search range in the poor strategy to the circumference range of the individual and the parent target individual, and a rotation crossover operator and a binomial poor operator were combined. Finally, an improved adaptive DE algorithm based on a multi-angle search rotation crossover strategy was obtained. The research will improve the DE algorithm to optimize the testing of multidimensional circuits. It can be noted that the improved average precision value is 0.9919 when comparing the precision recall curves of the DE algorithm before and after the change, demonstrating a significant improvement in accuracy and stability. The fitness difference of the 30-dimensional problem is discovered to be between 0.25 × 103 and 0.5 × 103 by comparing the box graphs of the 30-dimensional problem with that of the 50-dimensional problem. On the 50-dimensional problem, when calculating the F4–F10 function, the fitness difference of the improved DE algorithm is 0.2 × 104–0.4 × 104. In summary, the improved DE algorithm proposed in this study compensates for the shortcomings of traditional algorithms in complex problem calculations and has also achieved significant optimization results in multidimensional circuit testing.

DESIGNING TECHNO-ECONOMIC OFF-GRID PHOTOVOLTAIC SYSTEM USING AN IMPROVED DIFFERENTIAL EVOLUTION ALGORITHM

Conventional power generation is one of the main contributors to the phenomenon of the greenhouse effect. This has led to a diversification of electricity sources including environmentally friendly energy sources such as solar energy. Off-grid PV systems have gained some traction due to their cost-effectiveness for rural communities. However, the intermittent nature of solar is the main challenge to developing the off-grid PV system. Moreover, the high capital cost of PV systems as well as the storage batteries becomes the main concern for all PV users. Thus, this study aims to optimize the size of the PV system and battery simultaneously and design a cost-effective off-grid photovoltaic system considering various aspects such as battery power, solar irradiance, and PV panel selection while ensuring system reliability. The proposed system was optimized using improved Differential Evolution (DE) and its effectiveness was tested by comparing the results with Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). The Improved DE algorithm provides the highest average cost savings compared to other algorithms, which is $500 per year. It is recommended that this method is very useful in the optimization of off-grid PV systems, considering other uncertainties that affect PV system performance.

Decoupling Control of Six-Pole Hybrid Magnetic Bearing Based on LM Neural Network Inverse System Optimized by Improved Differential Evolution Algorithm

In order to solve the problems of strong coupling and nonlinearity of the hybrid magnetic bearings for flywheel energy storage, a novel decoupling control combining Levenberg Marquardt neural network inverse system (LMNNIS) with improved differential evolution (IDE) algorithm is proposed for the six-pole radial-axial hybrid magnetic bearing (HMB). Firstly, the structure and principle of the HMB are introduced, and the mathematical model of its radial-axial suspension forces is deduced. The IDE algorithm is used to optimize the initial model parameters of LMNNIS, and the displacement and current data are collected and normalized to input into LMNNIS for training, so as to realize the decoupling control between the suspension forces of the HMB. Then, the simulation system is constructed, and the simulation experiments of the rotor floating and anti-interference are carried out, which show the convergence speed and anti-interference performance of IDE algorithm optimized LMNNIS are better than the traditional neural network inverse system. Finally, the verification experiments are carried out on the basis of the experimental platform, which prove the feasibility and reliability of the proposed method.

Improved Differential Evolution Algorithm for Sensitivity Enhancement of Surface Plasmon Resonance Biosensor Based on Two-Dimensional Material for Detection of Waterborne Bacteria

Due to the large number of waterborne bacteria presenting in drinking water, their rapid and accurate identification has become a global priority. The surface plasmon resonance (SPR) biosensor with prism (BK7)-silver(Ag)-MXene(Ti3T2Cx)-graphene- affinity-sensing medium is examined in this paper, in which the sensing medium includes pure water, vibrio cholera (V. cholera), and escherichia coli (E. coli). For the Ag-affinity-sensing medium, the maximum sensitivity is obtained by E. coli, followed by V. cholera, and the minimum is pure water. Based on the fixed-parameter scanning (FPS) method, the highest sensitivity is 246.2 °/RIU by the MXene and graphene with monolayer, and with E. coli sensing medium. Therefore, the algorithm of improved differential evolution (IDE) is obtained. By the IDE algorithm, after three iterations, the maximum fitness value (sensitivity) of the SPR biosensor achieves 246.6 °/RIU by using the structure of Ag (61 nm)-MXene (monolayer)-graphene (monolayer)-affinity (4 nm)-E. coli. Compared with the FPS and differential evolution (DE) algorithm, the highest sensitivity is more accurate and efficient, and with fewer iterations. The performance optimization of multilayer SPR biosensors provides an efficient platform.

A new evolving operator selector by using fitness landscape in differential evolution algorithm

Due to the problems of low accuracy and increasing control parameters in the existing parameter adaptive methods of differential evolution (DE) algorithm, in this paper a mutation operator selector and a parameter selector are proposed through Fitness Landscape (FL) analysing. At first, the performance differences of the two categories of mutation operators named DE/best/1 and DE/current-to-rand/1 were analyzed on many test problems. Secondly, the relationship between the FL and mutation operator is founded by using ensemble learning and decision tree, and achieved a classifier named mutation operator selector. Thirdly, the relationship between the FL and algorithm parameters is founded by using a neural network, and then a classifier named parameter selector is achieved. Finally, the improved DE algorithm equip with the two selectors is tested on the CEC2017 benchmark set. The results show that the proposed improved DE algorithm is outperforms both the basis DE algorithm and other three state-of-the-arts algorithms.

Joint inversion of VES and Rayleigh wave data based on improved DE algorithm for near surface exploration

PurposeVertical electrical sounding (VES) and Rayleigh wave exploration are widely used in the exploration of near-surface structure, but both have limitations. This study aims to make full use of the advantages of the two methods, reduce the multiple solutions of single inversion and improve the accuracy of the inversion. Thus, a nonlinear joint inversion method of VES and Rayleigh wave exploration based on improved differential evolution (DE) algorithm was proposed.Design/methodology/approachBased on the DE algorithm, a new initialization strategy was proposed. Then, taking AK-type with high-velocity interlayer model and HA-type with low-velocity interlayer model near the surface as examples, the inversion results of different methods were compared and analyzed. Then, the proposed method was applied to the field data in Chengde, Hebei Province, China. The stratum structure was accurately depicted and verified by drilling.FindingsThe synthetic data and field data results showed that the joint inversion of VES and Rayleigh wave data based on the improved DE algorithm can effectively improve the interpretation accuracy of the single-method inversion and had strong stability and large generalizable ability in near-surface engineering problems.Originality/valueA joint inversion method of VES and Rayleigh wave data based on improved DE algorithm is proposed, which can improve the accuracy of single-method inversion.

Novel Formulations and Improved Differential Evolution Algorithm for Optimal Lane Reservation With Task Merging

This paper investigates a new lane reservation problem with task merging that consists of optimally determining which lanes in a transportation network have to be reserved and designing reserved lane-based routes in the network for time-crucial transport tasks. Part of the tasks whose destinations are geographically close is merged to reduce the number of vehicles and transport costs. Reserved lanes can reduce the travel time of task vehicles passing through them, while they will generate negative impact on normal traffic, such as traffic delay to the vehicles on adjacent non-reserved lanes. The objective is to minimize the total negative impact of all reserved lanes. For this problem, two new integer linear programming (ILP) models are first developed. The complexity of the problem is proved to be NP-hard. Since commercial solver (like CPLEX) is time-consuming for solving it when the problem size increases, a fast and effective improved differential evolution algorithm (IDEA) is developed based on explored problem properties. Extensive experimental results for a real-life case and benchmark instances of up to 500 nodes in the network and 30 transport tasks show the favorable performance of the IDEA, as compared to CPLEX, differential evolution algorithm and genetic algorithm. Management insights are also drawn to support practical decision-making.

A New Fuzzy Sliding Mode Control Method for Permanent Magnet Synchronous Motor Servo System Based on Optimization of Fuzzy Rules

Aiming at the problems of inherent chattering of traditional sliding mode control system of permanent magnet synchronous motor and further improving the control precision, a new fuzzy exponential reaching law sliding mode control method optimized by improved differential evolution (DE) algorithm (DEFSMC) is proposed in this article. A new hyperbolic tangent function with fuzzy boundary layer is proposed to instead of the traditional switching function, and the improved DE algorithm is used to optimize the fuzzy rules of parameters in sliding mode controller. Simulation and experimental results prove that the proposed strategy can effectively reduce the chattering and overshoot, and improve the response speed and robustness of the system. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

DEHM: An Improved Differential Evolution Algorithm Using Hierarchical Multistrategy in a Cybertwin 6G Network

Differential evolution (DE) algorithm can be used in edge/cloud cyberspace to find an optimal solution due to its effectiveness and robustness. With the rapid increase of the mobile traffic data and resources in a cybertwin-driven 6G network, the DE algorithm faces some problems such as premature convergence and search stagnation. To deal with the problems mentioned above, in this article, an improved DE algorithm based on hierarchical multistrategy in a cybertwin-driven 6G network (denoted by DEHM) is proposed. Based on the fitness value of the population, DEHM classifies the population into three sub-population. Regarding each sub-population, DEHM adopts different mutation strategies to achieve a tradeoff between convergence speed and population diversity. In addition, a new selection strategy is presented to ensure that the potential individual with good genes is not lost. Experimental results suggest that the DEHM algorithm surpasses other benchmark algorithms in the field of convergence speed and accuracy. The proposed DEHM is expected to be leveraged in edge/cloud cyberspace, aiming at reducing energy costs and improving resource utilization.

Fractional‐order system identification based on an improved differential evolution algorithm

AbstractWith the continuous increasing of system modeling accuracy and control performance requirements, the fractional‐order models are applied to describe the dynamic characteristics of the real systems more accurately over traditional integer‐order models. Traditional identification algorithms for fractional‐order system require stringent information on the derivatives of the objective function and initial values of the parameters, which is difficult in practical applications. The differential evolution (DE) algorithm has the advantage of simple implementation and superior performance for solving multi‐dimensional complex optimization problems which is suitable for the identification of fractional‐order systems. Aiming at improving the solution accuracy and convergence speed, an improved DE (IDE) algorithm for fractional‐order system identification is proposed. The movement strategy of the marine predator algorithm (MPA) and the mutation strategy of randomly selecting one from the optimal individual population as the basis vector are both adopted in this proposed IDE algorithm. The parameter information of the successfully mutated individual is archived during the iteration process. The scaling factor and crossover probability factor are adaptively adjusted according to the archived information to enhance the best solution accuracy obtained in the search process. By testing 13 sets of unimodal and multimodal functions with high‐performance optimization algorithms, the accuracy performance of the proposed IDE solution is verified. The IDE algorithm is applied to identify the parameters of the fractional‐order system of permanent magnet synchronous motor with simulation and experiment. The identification results clearly show the effectiveness of the proposed methodology.

Application of an adaptive PID controller enhanced by a differential evolution algorithm for precise control of dissolved oxygen in recirculating aquaculture systems

In aquaculture, the dissolved oxygen (DO) content of a water body is important for the growth of aquatic products and thus needs to be precisely controlled. For this purpose, through an open-loop experiment of DO aeration under different airflow rates, empirical transfer function models that can fully describe the dynamic response relationship between aeration flow rate and DO content were established. Based on these models, this study proposed a differential evolution (DE) algorithm-optimised radial basis function (RBF) neural network proportional integral derivative (PID) controller (DE-RBF-PID). The proposed controller has two optimisation parts. The first part is devoted to finding the optimal initial parameters of PID using an improved DE algorithm. The second part utilises the powerful learning ability of the RBF neural network to adjust the PID parameters online, which can not only eliminate overshoots, but also improve the controller adaptability. The simulation results for a typical DO nonlinear control system demonstrated the superiority of the proposed DE-RBF-PID controller over conventional PID and RBF-PID controllers. Therefore, this controller can be applied for precise tracking control of DO in complex circulating aquaculture systems. • The transfer function models of the control process for DO were established. • An adaptive PID controller enhanced by DE algorithm was proposed. • This proposed controller was used for DO control in circulating aquaculture. • This work can provide theoretical basis and accumulate experience for practical application.

A Cable Layout Optimization Method for Electronic Systems Based on Ensemble Learning and Improved Differential Evolution Algorithm

In this article, a method for solving cable layout optimization problems in electronic systems based on ensemble learning (EL) and improved differential evolution (DE) algorithm is proposed. Using this method, we produced two cable layout schemes with the considerations of the electromagnetic compatibility performance and the total length of cables. First, several different individual machine learning (ML) models for all output variables were established. On this basis, we established EL models with better performance than previous individual ML models. Then, aiming at the optimization problem presented in this article, an improved DE algorithm was proposed. On this basis, a method for solving cable layout optimization problems in electronic systems based on EL and the improved DE algorithm was proposed. Finally, the effectiveness of the proposed method was verified by two examples of electronic system cable layout optimization with different routing modes. Each example problem was solved using four different methods. The results indicate that the method proposed here outperformed existing methods.

Design and Optimization of a Vibrating Ring Gyroscope With High Shock Resistance by Differential Evolution

In this paper, a mode order optimized vibrating ring gyroscope (VRG) with high shock resistance is designed, and the improved optimization algorithm is proposed to optimize the structure design. The mode order of n=2 mode of the proposed VRG can be the first by structure design, which helps to enhance the anti-shock ability by increasing the translational mode frequency and avoid the excessive large n=2 mode frequency at the same time. The optimization method based on the differential evolution (DE) algorithm is developed to maximize the anti-shock ability of the VRG. At first, the shock response of VRG is analyzed. After representing the working principle and specific design of the designed VRG, the effect of the structural parameter of VRG on mode orders and frequencies of the n=2 mode and the translational mode as well as the shock response is simulated and analyzed. Finally, the structural design of VRG is transformed into a constrained optimization problem, and a modified DE algorithm integrated with the infeasible solution handling mechanism and the diversity enhancement strategy is applied to find feasible optimized structural parameters to maximize the shock resistance. The displacement and stress of optimized VRG structures under 10,000 g shock are small, which indicates the validity of the improved DE algorithm. Overall, the structure design and the optimization method in this paper can be a reference for other micromachined structure designs.

Goos–Hänchen shift enhancement based on an improved differential evolution algorithm

The Goos–Hänchen (GH) shift is one of the important aspects to evaluate the performance of multilayer surface plasmon resonance (SPR) sensors. However, the conventional SPR sensor design procedure based on the fixed parameter scanning (FPS) method is complex and time-consuming, and makes it difficult to gain the optimized design. In this paper, in order to design the optimal GH-shift-based SPR sensor, an improved differential evolution (IDE) algorithm based on chaos mapping, fitness elimination mechanism, nonlinear scale factor, and cross probability control strategy is proposed. By using such an IDE algorithm, the Ag‐ITO‐TMDCs‐graphene structure can be optimized. By the IDE algorithm, after 9 iterations, the maximum fitness value is obtained in the Ag‐ITO‐ M o S 2 -graphene structure, the maximum GH shift is 16591 λ , and the sensitivity is 3.3 × 10 8 λ / R I U . Compared with the FPS method, the GH shift is increased 192 times, and the sensitivity is increased 25,707.6 times. Compared with the DE algorithm, the number of iterations and the efficiency of the IDE algorithm are enormously improved as well. Such an algorithm provides a new, to the best of our knowledge, approach for designing a multilayer SPR sensor.

An adaptive fault detector strategy for scientific workflow scheduling based on improved differential evolution algorithm in cloud

With the increasing popularity and acceptance of cloud computing, it is being applied in services like executing large-scale applications, where cloud environment is selected by the scientific associations to easily execute the computation intensive workflows. However, cloud computing can have higher failure rates due to the larger number of servers and components filled with the intensive workloads. These failures may lead to the unavailability of virtual machines (VMs) for computation. Hence, this issue of fault occurrences can be tolerated by adopting an effective and efficient fault tolerant strategy. The goal of our research in this paper is to develop an adaptive fault detector strategy based on Improved Differential Evolution (IDE) algorithm in cloud computing that can minimize the energy consumption, the makespan, the total cost and, at the same time, tolerate up faults when scheduling scientific workflows. This proposed work applies an adaptive network-based fuzzy inference system (ANFIS) prediction model to proactively control resource load fluctuation that increases the failure prediction accuracy before fault/failure occurrence. In addition, it applies a reactive fault tolerance technique for when a processor fails and the scheduler must allocate a new VM to execute the workflow tasks. The experimental results show that compared with existing techniques, the proposed approach significantly improves the overall scheduling performance, achieves a higher degree of fault tolerance with high HyperVolume (HV) compared with the ICFWS, IDE, and ACO algorithms, minimizes the makespan, the energy consumption and task fault ratio, and reduces the total cost.

Differential evolution algorithm with wavelet basis function and optimal mutation strategy for complex optimization problem

The optimization performance of differential evolution(DE) algorithm significantly depends on control parameters and mutation strategy. However, it is difficult to set suitable control parameters and select reasonable mutation strategy for DE in solving an actual engineering optimization problem. To solve these problems, a new optimal mutation strategy based on the complementary advantages of five mutation strategies is designed to develop a novel improved DE algorithm with the wavelet basis function, named WMSDE, which can improve the search quality, accelerate convergence and avoid fall into local optimum and stagnation. In the proposed WMSDE, the initial population is divided into several subpopulations to exchange search information between the different subpopulations and improve the population diversity to a certain extent. The wavelet basis function and normal distribution function are used to control the scaling factor and the crossover rate respectively in order to ensure the diversity of solutions and accelerate convergence. The new optimal mutation strategy is used to improve the local search ability and ensure the global search ability. Finally, the proposed WMSDE is compared with five state-of-the-art DE variants by 11 benchmark functions. The experiment results indicate that the proposed WMSDE can avoid premature convergence, balance local search ability and global search ability, accelerate convergence, improve the population diversity and the search quality. Additionally, a real-world airport gate assignment problem is employed to further prove the effectiveness of the proposed WMSDE. The results show that it can effectively solve the complex airport gate assignment problem, and obtain airport gate assignment rate of 97.6%.

Pattern Synthesis of Linear Antenna Array Using Improved Differential Evolution Algorithm with SPS Framework

In this paper, an improved differential evolution (DE) algorithm with the successful-parent-selecting (SPS) framework, named SPS-JADE, is applied to the pattern synthesis of linear antenna arrays. Here, the pattern synthesis of the linear antenna arrays is viewed as an optimization problem with excitation amplitudes being the optimization variables and attaining sidelobe suppression and null depth being the optimization objectives. For this optimization problem, an improved DE algorithm named JADE is introduced, and the SPS framework is used to solve the stagnation problem of the DE algorithm, which further improves the DE algorithm’s performance. Finally, the combined SPS-JADE algorithm is verified in simulation experiments of the pattern synthesis of an antenna array, and the results are compared with those obtained by other state-of-the-art random optimization algorithms. The results demonstrate that the proposed SPS-JADE algorithm is superior to other algorithms in the pattern synthesis performance with a lower sidelobe level and a more satisfactory null depth under the constraint of beamwidth requirement.

Research on the Utilization of Metro Regenerative Braking Energy Based on an Improved Differential Evolution Algorithm

Urban metro trains have the characteristics of short running distance between stations and frequent starting and braking. A large amount of regenerative braking energy is generated during the braking process. The effective utilization of the regenerative braking energy can substantially reduce the total energy consumption of train operation. In this paper, we establish two integer programming models of train operation that maximize the overlap time between train traction and braking in peak hours and nonpeak hours. On this basis, an improved differential evolution (IDE) algorithm is developed for solving the two integer programming models. The results demonstrate that the overlap time increases by 51.44% after optimization using the IDE algorithm when the headway is set to 154 s in peak hours. The overlap time is further increased by 14.87% by optimizing the headway. In nonpeak hours, the overlap time of traction and braking of the trains in opposite directions at the same station is increased by optimizing the bidirectional departure interval, thereby reducing the total energy consumption of the system.

Solving Fuzzy Job-Shop Scheduling Problem Using DE Algorithm Improved by a Selection Mechanism

The emergence of fuzzy sets makes job-shop scheduling problem (JSSP) become better aligned with the reality. This article addresses the JSSP with fuzzy execution time and fuzzy completion time (FJSSP). We choose the classic differential evolution (DE) algorithm as the basic optimization framework. The advantage of the DE algorithm is that it uses a special evolutionary strategy of difference vector sets to carry out mutation operation. However, DE is not very effective in solving some instances of FJSSP. Therefore, we propose a novel selection mechanism augmenting the generic DE algorithm (NSODE) to achieve better optimization results. The proposed selection operator adopted in this article aims at a temporary retention of all children generated by the parent generation, and then selecting N better solutions as the new individuals from N parents and N children. Various examples of fuzzy shop scheduling problems are experimented with to test the performance of the improved DE algorithm. The NSODE algorithm is compared with a variety of existing algorithms such as ant colony optimization, particle swarm optimization, and cuckoo search. Experimental results show that the NSODE can obtain superior feasible solutions compared with solutions produced by several algorithms reported in the literature.