Differential Evolution Particle Swarm Optimization Research Articles

Differential evolutionary particle swarm optimization with orthogonal learning for wind integrated optimal power flow

This study develops a novel variant of particle swarm optimization (PSO), which improves its balance of exploration and exploitation by modifying neighborhood topology, self-adaptive parameter strategies and deep search, namely differential evolutionary evolution PSO with orthogonal learning (OL), i.e., DEEPSO-OL in short. Evolutionary computing can explore the solution space efficiently because of its self-evolving attribute as iteration continues. The OL enhances its exploitation by focusing on deeper search for promising solutions. It utilizes the concept of orthogonal experimental design (OED) which predicts the best combination of control variables without exhaustive evaluation of all possible combinations. In addition, to avoid premature convergence in a local optimum, a stochastic star topology for particles is proposed. Such topology ensures just enough communication among the best performing particles, while encouraging them to explore other spaces. The efficacy of the algorithm is evaluated through real-world scenarios such as optimal power flow (OPF) and wind integrated OPF, which are hard to solve with classical mathematical methods. The proposed algorithm is run on a modified IEEE 30-bus test system and compared to the state-of-the-art evolutionary computing algorithms for a variety of cost objective functions with high levels of non-linearity and non-convexity. The DEEPSO-OL demonstrates its performance to generate more accurate feasible solutions and construct promising and efficient search method for real-world complex optimization problems.

Identification of High and Low Voltage Ride-Through Control Parameters for Electromechanical Transient Modeling of Photovoltaic Inverter

The electromechanical transient model of a photovoltaic (PV) inverter’s high and low voltage ride-through has complex operating circumstances and a large number of control parameters, which makes parameter adjustment difficult. Furthermore, it is frequently challenging to identify a single set of control parameters that can successfully handle a variety of operating conditions. The Improved Differential Evolution Particle Swarm Optimization (IDEPSO) algorithm is proposed in this paper to provide a control parameter identification technique for high and low voltage ride-through that addresses these problems. Taking a 320kW PV inverter of a certain company as the research object, based on the specified current control strategy of high and low voltage ride-though, the parameters to be identified were determined by analyzing the influence of model parameters. Secondly, To enhance the algorithm’s capability to solve multidimensional optimization problems, convergence speed, and global search ability, the Differential Evolution (DE) algorithm’s search mechanism is incorporated into the Particle Swarm Optimization (PSO) algorithm, along with a non-fixed gradient inertia weight strategy for the algorithm’s inertia weight and the elite retention idea for the cross factor. Then, the objective function of the IDEPSO algorithm was built based on the concept of minimum deviation between simulation data and various groups of test data, and the significance of various working conditions was distinguished by weight division to improve the robustness of identification parameters. Finally, the identification parameters are imported into the PSASP program type 2 photovoltaic power station model, and the interval division and deviation calculation of the test data and simulation data are carried out. It is confirmed that the identification parameters meet the standards of the maximum variation permitted in GB/T 32892-2016 and are appropriate for a variety of working scenarios.

Trajectory planning of vibration suppression for hybrid structure flexible manipulator based on differential evolution particle swarm optimization algorithm

A differential evolution particle swarm optimization algorithm is proposed to address the vibration problem of a hybrid structure flexible manipulator after motion and stop. Firstly, the errors in the modeling process of the flexible manipulator were corrected, and its state variables were decomposed to establish dynamic and kinematic models. A sliding mode controller was then designed to track the trajectory. To find the optimal trajectory, a mapping function was constructed, and non-uniform interpolation points were selected. A normal distribution function was used to select discrete interpolation points, and the cubic spline interpolation was used to fit the trajectory. To prevent the particle swarm optimization algorithm from falling into local optima, the mutation and crossover operators of the differential evolution algorithm are incorporated into the algorithm, thereby expanding the search range. The effectiveness of this improved method was verified by comparing it with traditional particle swarm optimization algorithms. This study provides a new trajectory planning approach for the motion control of a hybrid structured flexible manipulator and has important practical significance.

Differential Evolution Particle Swarm Optimization for Phase-Sensitivity Enhancement of Surface Plasmon Resonance Gas Sensor Based on MXene and Blue Phosphorene/Transition Metal Dichalcogenide Hybrid Structure.

A differential evolution particle swarm optimization (DEPSO) is presented for the design of a high-phase-sensitivity surface plasmon resonance (SPR) gas sensor. The gas sensor is based on a bilayer metal film with a hybrid structure of blue phosphorene (BlueP)/transition metal dichalcogenides (TMDCs) and MXene. Initially, a Ag-BlueP/TMDCs-Ag-MXene heterostructure is designed, and its performance is compared with that of the conventional layer-by-layer method and particle swarm optimization (PSO). The results indicate that optimizing the thickness of the layers in the gas sensor promotes phase sensitivity. Specifically, the phase sensitivity of the DEPSO is significantly higher than that of the PSO and the conventional method, while maintaining a lower reflectivity. The maximum phase sensitivity achieved is 1.866 × 106 deg/RIU with three layers of BlueP/WS2 and a monolayer of MXene. The distribution of the electric field is also illustrated, demonstrating that the optimized configuration allows for better detection of various gases. Due to its highly sensitive characteristics, the proposed design method based on the DEPSO can be applied to SPR gas sensors for environmental monitoring.

An improved filtering algorithm for indoor localization based on DE-PSO-BPNN

Among the indoor localization algorithms, the algorithm based on traditional Back Propagation Neural Network (BPNN) has the problems of slow convergence and easy to fall into local optimum. It is difficult to apply the algorithm in noisy environments. Therefore, in this paper, we propose a novel indoor localization algorithm where the whole localization process is divided into two parts: data preprocessing and localization output. Data preprocessing means using filtering algorithm to process the Received Signal Strength Indication (RSSI) sequence. It is considered that the initial value of the received sequence has a significant impact on the performance of Kalman Filter (KF). An improved Kalman Filtering algorithm (DBSCAN-KF) is proposed based on the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. First, the RSSI values that are seriously disturbed by noise in the sequence are removed using the DBSCAN algorithm, and then the RSSI sequences are processed using KF so that the RSSI values can be closer to the theoretical values. The localization output part is to reduce the localization error caused by the BPNN. In this paper, the Differential Evolution (DE) algorithm and Particle Swarm Optimization (PSO) algorithm are combined, and the Differential Evolution Particle Swarm Optimization (DE-PSO) algorithm is proposed. The BPNN weights and thresholds are optimized in parallel, which improves the speed and ability of global optimization search and further avoids the shortcomings of traditional BPNNs that are prone to fall into local optimization in the training process. Experimental results show that the BPNN localization algorithm based on DBSCAN-KF improves the average localization accuracy by 0.26m compared with the BPNN localization algorithm without filtering. After filtering, the localization algorithm based on DE-PSO improved BPNN (DE-PSO-BP) improves the average localization accuracy by about 24% compared with the localization algorithm based on DE-PSO-BP. The localization algorithm based on DE-PSO-BP improves the average localization accuracy by about 61% compared with the traditional BPNN.

Prediction of asphalt pavement performance based on DEPSO-BP neural network

With the application of machine learning rapidly gaining popularity in computer science and other fields, neural network techniques have successfully simulated the performance of in-service pavements as they are efficient in predicting and solving nonlinear relationships and in dealing with uncertain large-area pavement problems. In this paper, we address the problem of the optimal timing of preventive maintenance of asphalt pavements to accurately predict the condition index (pavement condition index, PCI) of highway asphalt pavements and develop a highly accurate, long-period, multifactor prediction model with the suitability of preventive maintenance at its core. The prediction model is called differential evolution particle swarm optimization back propagation (DEPSO-BP) neural network, and the input dimension of the prediction model is determined by gray correlation analysis (GCA), and DEPSO is used to improve the search efficiency of BP neural network and the asphalt pavement usage performance with parameter continuity prediction model. Finally, the Qinglan Highway (G22) PCI of Gansu Province, China, is selected for example validation, and the prediction results are compared with those of the four models. The results show that the multifactor prediction model based on DEPSO-BP neural network has good generalization ability. This model is important for improving the economic efficiency of road maintenance, and can be used in the long-cycle process to provide model reference and scientific basis for the subsequent road maintenance budget application and decision-making scheme.

Heterogeneous differential evolution particle swarm optimization with local search

To develop a high performance and widely applicable particle swarm optimization (PSO) algorithm, a heterogeneous differential evolution particle swarm optimization (HeDE-PSO) is proposed in this study. HeDE-PSO adopts two differential evolution (DE) mutants to construct different characteristics of learning exemplars for PSO, one DE mutant is for enhancing exploration and the other is for enhance exploitation. To further improve search accuracy in the late stage of optimization, the BFGS (Broyden–Fletcher–Goldfarb–Shanno) local search is employed. To assess the performance of HeDE-PSO, it is tested on the CEC2017 test suite and the industrial refrigeration system design problem. The test results are compared with seven recent PSO algorithms, JADE (adaptive differential evolution with optional external archive) and four meta-heuristics. The comparison results show that with two DE mutants to construct learning exemplars, HeDE-PSO can balance exploration and exploitation and obtains strong adaptability on different kinds of optimization problems. On 10-dimensional functions and 30-dimensional functions, HeDE-PSO is only outperformed by the most competitive PSO algorithm on seven and six functions, respectively. HeDE-PSO obtains the best performance on sixteen 10-dimensional functions and seventeen-30 dimensional functions. Moreover, HeDE-PSO outperforms other compared PSO algorithms on the industrial refrigeration system design problem.

Stochastic Project Scheduling Optimization for Multi-stage Prefabricated Building Construction with Reliability Application

This study investigates a project scheduling problem of prefabricated building (PB) construction in an uncertain environment. Different from the traditional scheduling models in PB construction, we consider a complex multi-stage cooperation system including the production, transportation and assembly (PTA) phases. In this system, both activity durations and resource amounts are stochastic variables. By applying the reliability theory to the stochastic scheduling model innovatively, we formulate a duration reliability model to maximize the probability of non-delayed project completion, within the resource constraints. As the proposed model is a non-deterministic polynomial hard (NP-hard) problem, a hybrid meta-heuristic differential evolution particle swarm optimization (DEPSO) algorithm is developed, which is utilized the mutation factor of the differential evolution (DE) algorithm in the framework of the particle swarm optimization (PSO). Finally, a real-life example of a PB construction project is used to explore the performance of the proposed DEPSO algorithm. The result shows that the hybrid algorithm DEPSO can better find the global optimal solution in the multi-dimensional optimization problem.

Evaluating the risk of uncertainty in smart grids with electric vehicles using an evolutionary swarm-intelligent algorithm

In the last years, distributed clean energy resources such as solar irradiation, wind generation and electric vehicles as dispatchable units have been targeted as alternatives to fossil fuels in supplying the high energy demand of our society. Managing these distributed energy resources is a complex challenge, due to its uncertain behavior. In order to maintain a stable and profitable functioning of electrical systems, the development of strategies and algorithms to deal with the risk associated with this uncertainty deserves proper attention. This work addresses a risk-based energy resource management (ERM) optimization problem that deals with the day-ahead management, considering the occurrence of extreme events in a risk-averse strategy. In a risk-averse strategy, the worst case scenario cost is evaluated through the use of conditional value-at-risk (CVaR) method. To solve this ERM problem, we proposed the use of an improved version of Canonical Differential Evolutionary Particle Swarm Optimization (C-DEEPSO). This modification relies on the use of an adaptive velocity and on local search operators to improve search capability. The results indicated that, compared to two algorithms based on swarm intelligence, the proposed improved C-DEEPSO is able to provide solutions that not only reduce costs (in terms of thousands of monetary units) but also protects the aggregator against extreme scenarios.

A mutation operator self-adaptive differential evolution particle swarm optimization algorithm for USV navigation.

To keep the global search capability and robustness for unmanned surface vessel (USV) path planning, an improved differential evolution particle swarm optimization algorithm (DePSO) is proposed in this paper. In the optimization process, approach to optimal value in particle swarm optimization algorithm (PSO) and mutation, hybridization, selection operation in differential evolution algorithm (DE) are combined, and the mutation factor is self-adjusted. First, the particle population is initialized and the optimization objective is determined, the individual and global optimal values are updated. Then differential variation is conducted to produces new variables and cross over with the current individual, the scaling factor is adjusted adaptively with the number of iterations in the mutation process, particle population is updated according to the hybridization results. Finally, the convergence of the algorithm is determined according to the decision standard. Numerical simulation results show that, compared with conventional PSO and DE, the proposed algorithm can effectively reduce the path intersection points, and thus greatly shorten the overall path length.

A discrete differential evolution with local search particle swarm optimization to direct angle and aperture optimization in IMRT treatment planning problem

Intensity-modulated radiation therapy is a well-known technique for treating cancer patients worldwide. A treatment plan in this technique requires decision-making for three main problems: selection of beam angles, intensity map calculation, and leaf sequencing. Previous works investigated these problems sequentially. We present a new integrated framework for simultaneous decision-making of directions, intensities, and aperture shape, called direct angle and aperture optimization, and develop a mixed-integer nonlinear mathematical model for the problem. Due to the nonlinearity and the dimension of the problem, three efficient metaheuristics based on differential evolution (DE) called classic differential evolution (cDE), discrete differential evolution (dDE), and adaptive hybrid discrete differential evolution-particle swarm optimization (ahdDE-PSO) algorithms are designed to solve the problem. Parameters calibration is performed using the Taguchi design of experiments. The performance of the algorithms is evaluated by solving the problem for ten real cases of liver cancer disease from the TROTS data set. The performed ablation study and statistical analysis of computational results demonstrate that ahdDE-PSO is capable of finding high-quality treatment plans.

Intelligent Coordinated Control of PID-SMES and AVR based on Hybrid PSO-DE for Small Signal Stability Enhancement

Dynamic disturbances in the electric power system occur due to changes in the load that can change important parameter values, this results in loss of synchronization in multi-machine power systems, so a controller in the power system is needed to maintain a stable condition during dynamic disturbances. In this final project, a Proportional Integral Differential (PID)-Superconducting Magnetic Energy Storage (SMES) controller is useful for supplying or absorbing active power when there is a load change so that the frequency can be maintained continuously, and an Automatic Voltage Regulator (AVR) is in charge of regulating the voltage on the system. The PID controller in SMES is useful for setting the output parameters of SMES. Hybrid Differential Evolution - Particle Swarm Optimization (DE-PSO) optimization method is used to optimize the oscillation damping process. The results indicate that the use of PID SMES and AVR optimized using the DE-PSO hybrid algorithm has a better response. In the Suralaya generator unit, the overshoot is -0.0001395 pu, and the settling time is 12.4 seconds by using the optimal controller. Meanwhile, when it is not using the additional controller, the overshoot is -0.0004228 pu, and the settling time is more than 16 seconds.

Closed-Loop Tuning of Cascade Controller for Load Frequency Control of Multi-Area Distributed Generation Resources Optimized by ASOS Algorithm

This paper provides closed loop tuning of cascaded-tilted integral derivative controller (CC-TID) for load frequency control (LFC) of micro grid system. A micro grid system is the arrangement of distributed generation resources such as wind turbine generator (WTG), fuel cell (FC), aqua electrolyser (AE), diesel engine generator (DEG) and battery energy storage system (BESS). Different controllers such as proportional integral derivative (PID), two degree of freedom (2DOFPID), three degree of freedom (3DOFPID) and tilted integral derivative (TID) are used not only to sustain the disparity between real power generation and load demand but also accomplish zero steady state error to enrich the frequency and tie power regulations. The anticipated controller encompasses both the value of cascade (CC) and fractional order (FO) controls for better elimination of system instabilities. In the proposed CC-3DOFPID-TID controller, TID controller is castoff as a slave controller and 3DOFPID controller aided the role of dominant controller. The controlled parameters are optimized by adaptive symbiotic organism search (ASOS) algorithm for keen results of difficulties in LFC. To persist in ecosystem, symbiotic relations are predictable by organism through imitators. Further the dynamic behaviours of controller optimized by ASOS, teaching learning based optimization (TLBO) and differential evolution particle swarm optimization (DEPSO) are compared by extensive simulations in MATLAB/SIMULINK. Moreover the supremacy of proposed controller is performed through system dynamics comparison among PID, 2DOFPID, 3DOF-PID and CC-3DOFPID-TID controllers. Finally sensitivity of proposed controller has proven though random load perturbation.

Improving Particle Swarm Optimization Analysis Using Differential Models

This paper employs the approach of the differential model to effectively improve the analysis of particle swarm optimization. This research uses a unified model to analyze four typical particle swarm optimization (PSO) algorithms. On this basis, the proposed approach further starts from the conversion between the differential equation model and the difference equation model and proposes a differential evolution PSO model. The simulation results of high-dimensional numerical optimization problems show that the algorithm’s performance can be greatly improved by increasing the step size parameter and using different transformation methods. This analytical method improves the performance of the PSO algorithm, and it is a feasible idea. This paper uses simple analysis to find that many algorithms are improved by using the difference model. Through simple analysis, this paper finds that many AI-related algorithms have been improved by using differential models. The PSO algorithm can be regarded as the social behavior of biological groups such as birds foraging and fish swimming. Therefore, these behaviors described above are an ongoing process and are more suitable for using differential models to improve the analysis of PSO. The simulation results of the experiment show that the differential evolution PSO algorithm based on the Runge–Kutta method can effectively avoid premature results and improve the computational efficiency of the algorithm. This research analyzes the influence of the differential model on the performance of PSO under different differenced conditions. Finally, the analytical results of the differential equation model of this paper also provide a new analytical solution.

Hybrid differential evolution particle swarm optimization (DEA-DCWPSO) for resource-constrained multi-project scheduling problem

In this paper, we studied the resource constrained project scheduling problem, and the research object is extended to the multi-project environment. On the basis of multi-project priority evaluation, with the goal of minimizing the weighted duration of multi-project, a multi-project schedule planning model is constructed. Through reasonable scheduling of multiple parallel projects sharing resources under resource constraints, it provides a decision-making basis for project managers to allocate resources reasonably under resource constraints to meet the duration requirements of each project and to shorten the weighted total duration of multiple projects as much as possible. A two-stage hybrid differential evolution particle swarm optimization algorithm is used to solve the model. In the first stage, differential evolution algorithm is used to produce new individuals, and in the second stage, particle swarm optimization algorithm uses a new speed update formula. In the first stage, in order to ensure that the optimal individual will not be destroyed by crossover and mutation, and to maintain the convergence of differential evolution algorithm, we try to introduce Elitist Retention (ER) strategy into differential evolution algorithm. In the second stage, we use a kind of particle swarm optimization algorithm with dynamically changing inertia weight. Through the dynamic changing inertia weight, the global search and local search ability of the algorithm can be adjusted flexibly. The case verification shows that the hybrid differential evolution particle swarm optimization algorithm can be used to solve the RCMPSP model more effectively.

Mutual learning differential particle swarm optimization

This study proposes a mutual learning strategy to develop a high performance hybrid algorithm based on particle swarm optimization and differential evolution. In the mutual learning strategy, the position information in PSO subswarm is employed for DE mutation, and the DE individuals are used to construct learning exemplar for PSO subswarm together with particles’ historical best position. A novel elite DE mutation is proposed to speed up the convergence rate of DE subswarm. Based on mutual learning technique, the mutual learning differential evolution particle swarm optimization (MLDE-PSO) is proposed. To evaluate the performance of MLDE-PSO, three groups of test functions are employed, namely thirteen basic functions, thirteen rotated basic functions and thirty CEC2017 functions. The test results are compared with three state-of-the-art PSO algorithms, three recently PSO algorithms and DE/rand/1. The test results indicate that the proposed MLDE-PSO performs better than the other seven comparison algorithms, especially on rotated functions and CEC2017 functions. The rotation test shows that MLDE-PSO is not very sensitive to rotation transformation.

Highly Directive Array Pattern Synthesis in Different phi Planes of a Large CCRAA Using Array Thinning Technique

This paper presents a pattern synthesis method of a sizeable concentric circular ring array (CCRAA) of isotropic antennas using Evolutionary Algorithms. In this method, the array is thinned using the optimum set of binary excitations to achieve the desired highly directive pencil beam patterns with lower peak side lobe level(SLL). The half-power beam width and first null beam width is kept constant to obtain such highly directive beam patterns with lower peak SLL. This pattern is not synthesized to a particular azimuth plane rather in four different ' planes from entire azimuth planes. The isotropic elements are uniformly spaced in the concentric ring. The achieved set of optimum amplitudes are constructed with either 1 or 0 using Differential Evolutionary Algorithm(DE), Genetic Algorithm (GA), and Particle Swarm Optimization Algorithm (PSO). These excitations show the state of the elements. The elements are in “ON” state or in “OFF” state depending upon the excitation ‘1’ or ‘0’. It is also helpful to reduce the complexity of the feed networks. The excitations are also verified in the whole range (0o <phi<360o) of ' planes by selecting four phi planes arbitrarily. The outcomes established the superiority of GA and DE over PSO and also the effectiveness of the proposed method.

Hybrid Differential Evolution Particle Swarm Optimization Algorithm for Solving Resource Leveling Problem of Multi-project with Fixed Duration

This paper attempts to substitute Resource Leveling Problem (RLP) into multi-project environment and construct Resource Leveling Problem of Multi-project (RLPMP) model with the goal of minimizing the sum of weighted mean square deviations of multi-resource requirements. A two-stage hybrid differential evolution particle swarm optimization algorithm is used to solve the model. In the first stage, differential evolution algorithm is used to produce new individuals, and in the second stage, particle swarm optimization algorithm uses a new speed update formula. In the first stage, in order to ensure that the optimal individual will not be destroyed by crossover and mutation, and to maintain the convergence of differential evolution algorithm, we try to introduce Elitist reservation (ER) strategy into differential evolution algorithm. In the second stage, we use a kind of Particle Swarm Optimization (PSO) algorithm with dynamic inertia weight. Through the dynamic change of inertia weight, the global search and local search ability of the algorithm can be adjusted flexibly. The case verification shows that the hybrid differential evolution particle swarm optimization algorithm can effectively solve the RLPMP model, and then effectively improve the balance of multi-project resources.

Optimal Power Flow Considering Global Voltage Stability Based on a Hybrid Modern Heuristic Technique

Integrating large renewable energy to grid complicates power systems’ steady-state operation which leads to the high risk of voltage instability due to its intermittent and stochastic properties. The steady-state voltage stability margin (VSM) can be measured by the smallest singular value (SSV) of the load flow Jacobian matrix. Unlike other voltage stability indices such as L-index which shows the probability of voltage collapse for a particular bus, namely, local stability index, SSV represents the global voltage stability and the smaller the value is, the riskier the whole system's stability is. Voltage stability constrained-optimal power flow (VSC-OPF) is an effective tool to stabilize system voltage. Yet VSC-OPF is a highly non-linear and non-convex problem because of AC power flow and implicit SSV constraints. Such challenge is tackled, in this work, by a novel hybrid heuristic method, differential evolutionary particle swarm optimization (DEEPSO) which can easily formulate explicit constraints and objective functions to obtain near-optimal solutions efficiently. Several case studies are conducted on the IEEE 30-bus system, and they demonstrate the effectiveness of the hybrid technique and presents some insights on voltage profiles under various system operating condition.

Parameters estimation of horizontal multilayer soilsusing a heuristic algorithm

The grounding grid is buried in horizontal multilayer soils, so accurate parameters (resistivity , thickness, the number of soil layers) estimation of the soil is the basis for accurately calculating the grounding parameters and design of grounding grids. At present, the parameters estimation is usually solved by non-heuristic algorithms and heuristic algorithms. However, existing non-heuristic algorithms depend too much on the initial value and conventional heuristic algorithms could deviate from the correct solution too far, which would easily fall into local optimal solution, causing calculation errors. To solve the above problem, this paper first studies the relationship between the apparent soil resistivity and soil parameters based on the Wenner's method. Then, an innovative PSO-DE (Particle Swarm Optimization-Differential Evolution) optimization algorithm and its initialization method are proposed. The results of PSO-DE, conventional heuristic intelligent optimization algorithms, CDEGS, and literatures are compared, which verifies the superiority and accuracy of the PSO-DE. Therefore, the contribution of this work can lay a solid theoretical foundation for grounding parameters calculation.