Differential Evolution Optimization Method Research Articles

Optimized fuzzy PI controller for variable speed wind turbine using DE algorithm

To design an optimal fuzzy proportional-integral (PI) controller for the variable speed wind turbine systems, a new differential evolution (DE) algorithm approach is developed in this paper. We have investigated a fuzzy PI controller, in which fuzzy rules are applied to adapt the parameters of the PI controller founded on the error and its first-time derivative. The fuzzy PI controller's inputs and outputs are tuned using the DE optimization method. The superiority of the suggested (DE fuzzy PI) controller has been proved by comparing the results with (fuzzy PI) and only the PI controller applied to the wind turbine system. In comparison to a fuzzy controller with parameters selected by a human operator, the numerical validation results of the suggested approach (DE fuzzy PI) have shown good performance in terms of robustness, pursuit, and response time.

Identification of COVID-19 spread mechanisms based on first-wave data, simulation models, and evolutionary algorithms.

The COVID-19 epidemic has shown that efficient prediction models are required, and the well-known SI, SIR, and SEIR models are not always capable of capturing the real dynamics. Modified models with novel structures could help identify unknown mechanisms of COVID-19 spread. Our objective is to provide additional insights into the COVID-19 spread mechanisms based on different models' parameterization which was performed using evolutionary algorithms and the first-wave data. Data from the Our World in Data COVID-19 database was analysed, and several models-SI, SIR, SEIR, SEIUR, and Bass diffusion-and their variations were considered for the first wave of the COVID-19 pandemic. The models' parameters were tuned with differential evolution optimization method L-SHADE to find the best fit. The algorithm for the automatic identification of the first wave was developed, and the differential evolution was applied to model parameterization. The reproduction rates (R0) for the first wave were calculated for 61 countries based on the best fits. The performed experiments showed that the Bass diffusion model-based modification could be superior compared to SI, SIR, SEIR and SEIUR due to the component responsible for spread from an external factor, which is not directly dependent on contact with infected individuals. The developed modified models containing this component were shown to perform better when fitting to the first-wave cumulative infections curve. In particular, the modified SEIR model was better fitted to the real-world data than the classical SEIR in 43 cases out of 61, based on Mann-Whitney U tests; the Bass diffusion model was better than SI for 57 countries. This showed the limitation of the classical models and indicated ways to improve them. By using the modified models, the mechanism of infection spread, which is not directly dependent on contacts, was identified, which significantly influences the dynamics of the spread of COVID-19.

K-Means-Based Multigroup Differential Evolution Optimization Framework for Design of MIMO Antenna With Decoupling Elements

A novel differential evolution optimization method named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">K</i> -means-based multigroup differential evolution (KMGDE) framework is proposed for multiple-input–multiple-output (MIMO) antenna design. The KMGDE algorithm divides the population into three groups using the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">K</i> -means clustering method in each iteration. Different mutation strategies are assigned for each group according to its average fitness value. The groups are then combined for crossover operation with an adaptive crossover rate value to balance local search and global search. The fitness function considering the characteristics of the MIMO antenna is proposed to speed up optimization. The performance of the proposed method is evaluated and compared with six state-of-the-art optimization algorithms using an MIMO antenna example. The optimization results and the experimental results show that the proposed KMGDE algorithm has a faster convergence than state-of-the-art optimization algorithms, which significantly improves the efficiency of MIMO antenna design.

Parameter Identification of Chaboche Model for Aluminum Alloy Sheets Based on Differential Evolution Algorithm

Springback prediction is one of the most challenging in finite element analysis for sheet metal forming processes. The demand requests the development of a kinematic hardening model and parameter identification. This study presents a schematic strategy to identify parameters of Chaboche’s kinematic hardening model based on a differential evolution optimization method. To this goal, several tension-compression (TC) tests were conducted to observe the Bauchinger’s effects and kinematic hardening behaviors of two aluminum alloy sheets: AA6022-T6 and AA7075-T76. A Python code is developed to apply the proposed method in identifying parameters of the kinematic hardening model. The calibrated material models were implemented in Abaqus software to simulate V-bending and U-bending tests for the investigated materials. The predictions for springback amount match well with the experimental measurements, which verifies the effectiveness of the presented identificationstrategy.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.

Optimum vertical location and design of multiple tuned mass dampers under seismic excitations

An efficient optimum vertical location and design method of multiple tuned mass dampers (MTMDs) is proposed in order to reduce the response of building structures under seismic excitation. Governing equations are derived in frequency domain in terms of random vibration theory and probabilistic critical excitation method. In order to determine the location and optimum parameters of each tuned mass damper (TMD) which are mass, stiffness and damping coefficient, both top storey mean square absolute acceleration and displacement of shear building are chosen as the objective functions to be minimized via Differential Evolution (DE) optimization method. It is assumed that there is one TMD on each storey at the initial stage of the method. During the optimization, if the mass or stiffness parameters convergence to zero on a specific storey, then TMD is eliminated, so that optimum placement can be achieved. The sum of the critical effects corresponding to the selected bandwidths in the first, second and third frequency peak regions of the structure is taken into account, thus the high mode behaviors are also controlled. In order to understand the performance of proposed method, shear building model with multiple TMD is tested using different earthquake acceleration records and the findings are compared with some other studies available in the literature. The results show that the optimal MTMD design obtained from proposed method is very effective in reducing the dynamic response of building structure.

Energy Community Measures Evaluation via Differential Evolution Optimization

Abstract Energy communities are paving the way for new cooperation opportunities related to energy consumption and energy production. Individuals unite in energy communities to reduce the costs related to energy consumption. Although previous work has mainly focused on energy exchange inside the community. This work aims to investigate the Pareto-optimal solutions to the transformation of a historical district into an energy community. For energy efficiency and production measure calculation, a system dynamics model is developed. Multiobjective differential evolution optimization method is employed for the evaluation of energy efficiency and production measures with a focus on net present value, self-sufficiency, annual emission reduction, and specific heat consumption. The optimization target functions can be increased at a cost in net present value. Replacement of household appliances and windows enables significant energy demand reductions while maintaining positive net present value. Electricity production from photovoltaic panels offers an additional pathway to increase selfsufficiency share while maintaining positive net present value.

Global Sliding-Mode Control with Fractional-Order Terms for the Robust Optimal Operation of a Hybrid Renewable Microgrid with Battery Energy Storage

The efficiency of hybrid microgrid systems is drastically affected by the number of power electronics converters interfacing with its components. Integrating distributed energy sources with microgrids with the optimal number of converters is crucial to minimizing the switching losses and power conversion stages, thereby improving the efficiency of the systems. This paper considers an efficient and economical configuration for a wind/solar photovoltaic (PV) system integrated with a battery energy storage system (BES). The PV system is connected directly to the DC-link, thus lowering the losses and cost by eliminating the PV boost converter. In the literature, only a few publications have investigated this effective microgrid configuration. In addition, none of the publications have developed a nonlinear control approach for the microgrid configuration. Due to the greater flexibility of fractional calculus in speeding up the system response and improving the robustness, this article proposes a global sliding-mode control method with fractional-order terms (GSMCFO) to enhance the transient, steady-state, and robust operation of the hybrid microgrid. This controller provides the maximum power point tracking (MPPT) of both the solar PV and wind power generators, regulates the DC-link voltage, ensures proper power transfer to the grid, and maintains the power balance. In addition, the GSMCFO guarantees the global stability of the hybrid microgrid. Furthermore, considering the simplicity, robustness, few control variables, and fast convergence rate of the differential evolution (DE) optimization method, it is utilized to optimize the performance of the GSMCFO. The proposed hybrid microgrid configuration under the action of the GSMCFO was simulated in MATLAB/SIMULINK. Various scenarios were investigated to illustrate the feasibility of the proposed scheme. The simulation results show that the GSMCFO can achieve superior dynamic performances than the proportional–integral (PI) controller with zero overshoot, a shorter settling time, and stronger robustness, thus improving the power balance of the hybrid microgrid.

Online decision making and path planning framework for safe operation of unmanned aerial vehicles in urban scenarios

As the potential for deploying low-flying unmanned aerial vehicles (UAVs) in urban spaces increases, ensuring their safe operations is becoming a major concern. Given the uncertainties in their operational environments caused by wind gusts, degraded state of health, and probability of collision with static and dynamic objects, it becomes imperative to develop online decision-making schemes to ensure safe flights. In this paper, we propose an online decision-making framework that takes into account the state of health of the UAV, the environmental conditions, and the obstacle map to assess the probability of mission failure and re-plan accordingly. The online re-planning strategy considers two situations: (1) updating the current trajectory to reduce the probability of collision; and (2) defining a new trajectory to find a new safe landing spot, if continued flight would result in risk values above a pre-specified threshold. The re-planning routine uses the differential evolution optimization method and takes into account the dynamics of the UAV and its components as well as the environmental wind conditions. The new trajectory generation routine combines probabilistic road-maps with B-spline smoothing to ensure a dynamically feasible trajectory. We demonstrate the effectiveness of our approach by running UAV flight simulation experiments in urban scenarios.

Optimization method for non-cooperative iris recognition task using Daugman integro-differential operator

We considered the issues arising when Daugman’s integrodifferential operator is used to localize iris edges. Daugman’s integro-differential operator is a widely common method to localize the iris, however, problems of the operator optimization poorly presented in the literature. The article considers existing methods of optimization of the operator applied at the iris recognition step. Based on the provided research we proposed using Nelder-Mead and Differential Evolution methods to optimize the integro-differential operator. The problems of the iris localization and their solving methods were considered. The article focuses attention on non-cooperative iris recognition. The very general boundary conditions based on iris’s anatomy which are not dependent on captured image properties were defined. The results of the comparative analysis of the accuracy and performance of selected optimization methods of Daugman’s integrodifferential operator were presented at the experimental results chapter. It was found that the Differential evolution optimization method gives fine performance and correctness. It was concluded that the Differential evolution is expedient as Daugman’s integro-differential operator optimization method.

Optimum design of 3R robot manipulador by using Improved Differential Evolution implemented in parallel computation

&#x0D; &#x0D; &#x0D; In recent decades the great interest in Evolutionary Algorithms (EAs) has boosted their development leading to a significant improvement in their efficiency and applicability. Thus, EAs have been applied to solve optimization problems in different areas of knowledge. A promising optimization method known as Differential Evolution (DE), which belongs to the class of AEs, has attracted the attention of researchers. The DE algorithm is simple, robust and efficient. However, by testing with classical optimization problems noticed that sometimes the results obtained with DE are not as satisfactory as expected or that in many cases the algorithm ends the search for the optimal solution prematurely. Recently, with the advancement and greater availability of computer technology, the scientific community has been thinking about the implementation of optimization algorithms in parallel in order to reduce the processing time. The main objective of this paper is to present an improvement of the Differential Evolution optimization method, proposing modifications to the basic algorithm by using shuffled complex and making it able to work with parallel computing. The proposed methodology is applied to the optimal design of an orthogonal 3R robot manipulator that takes into account the characteristics of its workspace. For this purpose, a multi-objective optimization problem is formulated to obtain the optimal geometric parameters for the robot. The maximum workspace volume, the maximum system stiffness and the optimum dexterity are considered as the multi-objective functions. The results show that the procedure represents a promising alternative for the type of problem presented above.&#x0D; &#x0D; &#x0D;

A Comparison of Extremal Optimization, Differential Evolution and Particle Swarm Optimization Methods for Well Placement Design in Groundwater Management

When designing a well field for efficiently extracting groundwater or petroleum, it is common for designers to rely on computational optimization methods to determine the optimal placement of wells. The goal of these methods is to find a well-field solution that maximizes the value of a defined objective function, and to do so while utilizing the least amount of computational effort. To achieve this, researchers have developed algorithms based on a wide range of heuristics. Within groundwater management, popular methods include particle swarm optimization (PSO) and genetic algorithms such as differential evolution (DE). This study seeks to investigate a recently developed method called Extremal Optimization for Well Placement Problems (EO-WPP), and to compare its performance with established methods like PSO and DE. EO-WPP is an optimization method based on the extremal optimization (EO) algorithm. EO optimizes by iteratively identifying and modifying the least effective components of a solution. By following this heuristic, the EO algorithm has the potential to quickly find optimal solutions while requiring minimal computational effort. To test this, the performance of DE, PSO and EO-WPP was compared on four benchmark problems. Two of these are the Rastrigin and the Rosenbrock benchmark functions. These functions were used because of their quick evaluation and their popularity in optimization literature. The third benchmark is a synthetic groundwater model, built to test the methods under the context of groundwater management. The final benchmark is a field problem using the Aberdeen groundwater model in South Dakota. The results reveal that EO-WPP was able to outperform DE and PSO on all tested benchmarks. EO-WPP is an effective and efficient optimization tool for well placement design in groundwater management.

Wind Power Prediction of Kernel Extreme Learning Machine Based on Differential Evolution Algorithm and Cross Validation Algorithm

As fossil fuel is being depleted, the percentage of wind power capacity in total electricity generation is increasing. In order to improve the absorption capacity of wind power, wind power prediction has been introduced. Aiming at the disadvantage of low prediction accuracy and unstable model of traditional extreme learning machine (ELM), a kernel extreme learning machine based on differential evolution (DE) and cross validation optimization method is proposed to predict short-term wind power generation. Firstly, the average mean square error (MSE) verified by k folding and cross validation is adopted as the error function of the model to improve the stability and generalization performance of the model. Secondly, differential evolution algorithm is used to optimize the regularization coefficient and kernel width of the kernel extreme learning machine with cross validation and improve the precision of model is 8.34%. Finally, compared with the application of extreme learning machine with genetic algorithm and cross validation to a wind farm prediction case in northwest China, the experimental results show that the convergence rate of this method is twice that of genetic algorithm (GA) optimization algorithm, and the accuracy is higher.

Advances in global optimization of high brightness beams

High brightness electron beams play an important role in accelerator-based applications such as driving X-ray free electron laser (FEL) radiation. In this paper, we report on advances in global beam dynamics optimization of an accelerator design using start-to-end simulations and a new parallel multi-objective differential evolution optimization method. The global optimization results in significant improvement of the final electron beam brightness.

Optimization of Module Parameters for PV Power Estimation Using a Hybrid Algorithm

This article proposes a novel method to estimate the optimal parameters and power outputs for photovoltaic (PV) power generation. Accurate estimation for PV power generation allows efficient scheduling to meet the load demand and reduces the effect of uncertainty for a microgrid. The parameters that are provided by the PV manufacturer have a nonlinear relationship with power output and may vary with the aging of the PV cells. To allow finer and more accurate estimation for PV power output, the parameters of the single-diode $R_{p}$ model are transformed into 13 parameters under various weather conditions. The principal component analysis (PCA) and an assessment index are used to delete the parameters that have little effect on the output. Using the actual input/output data, a hybrid charged system search (HCSS) algorithm is then used to estimate the optimal parameters. When the parameters are optimized, the estimation for PV power output can be produced as long as the inputs are given. The proposed method is tested on two different PV power generation systems. To verify the performance of the proposed method, the results are compared with the results for the application of the traditional differential evolution (DE) and particle swarm optimization (PSO) methods.

Evaluation of PNN pattern-layer activation function approximations in different training setups

The processing of inputs in the first two layers of the probabilistic neural network (PNN) is highly parallel which makes it quite appropriate for hardware implementations with FPGA. One of the main inconveniences however remains the implementation of the nonlinear activation function of the pattern layer neurons. In the present study, we investigate the applicability of three approximations of the exponential activation function with look-up tables of different precision and the effect this has on the training process and the classification accuracy. Furthermore, seeking for a highly-parallel hardware-friendly algorithm for the automated adjustment of the spread factor $$\sigma _i$$, we investigated the performance of fifteen PNN training setups, which are based on the differential evolution (DE) or unified particle swarm optimization (UPSO) methods. The experimental evaluation was performed following a common experimental protocol, which makes use of the Parkinson Speech Dataset, as this research aims to support the development of portable medical devices that are capable to detect episodes with exacerbation in patients with Parkinson’s disease. The performance of the most successful setups is discussed in terms of error rates and from the perspective of the resources required for an FPGA-based implementation.

DYNAMIC SMART GRID COMMUNICATION PARAMETERS BASED COGNITIVE RADIO NETWORK

The demand for more spectrums in a smart grid communication network is a significant challenge in originally scarce spectrum resources. Cognitive radio (CR) is a powerful technique for solving the spectrum scarcity problem by adapting the transmission parameters according to predefined objectives in an active wireless communication network. This paper presents a cognitive radio decision engine that dynamically selects optimal radio transmission parameters for wireless home area networks (HAN) of smart grid applications via the multi-objective differential evolution (MODE) optimization method. The proposed system helps to drive optimal communication parameters to realize power saving, maximum throughput and minimum bit error rate communication modes. A differential evolution algorithm is used to select the optimal transmission parameters for given communication modes based on a fitness function that combines multiple objectives based on appropriate weights. Simulation results highlight the superiority of the proposed system in terms of accuracy and convergence as compared with other evolution algorithms (genetic optimization, particle swarm optimization, and ant colony optimization) for different communication modes (power saving mode, high throughput mode, emergency communication mode, and balanced mode).

Identification of Composite Demand Side Model With Distributed Photovoltaic Generation and Energy Storage

With the increasing penetration of distributed photovoltaic generation and energy storage systems in the demand side of the power system, new demand side model structures are necessary in order to better describe the dynamic performance of the power system. In this paper, a composite demand side model structure with load, distributed photovoltaic generation, and energy storage system together with a model parameter identification method are proposed to improve the traditional load model identification. The structure of the demand side model is proposed first and is further simplified so as to be identified at a high voltage level bus. The model parameter identifiability analysis is conducted based on the sensitivity method. The ambient signal data and disturbance data based model parameter identification method is proposed for the new demand side model structure using the differential evolution optimization method. The case study results for the WSCC 9 bus system show the effectiveness of the proposed model structure. Then, the case study results in a simplified 500-kV network of the Guangdong Power Grid show the effectiveness of the parameter identification method.

Shadowed Type-2 Fuzzy Systems for Dynamic Parameter Adaptation in Harmony Search and Differential Evolution Algorithms

Nowadays, dynamic parameter adaptation has been shown to provide a significant improvement in several metaheuristic optimization methods, and one of the main ways to realize this dynamic adaptation is the implementation of Fuzzy Inference Systems. The main reason for this is because Fuzzy Inference Systems can be designed based on human knowledge, and this can provide an intelligent dynamic adaptation of parameters in metaheuristics. In addition, with the coming forth of Type-2 Fuzzy Logic, the capability of uncertainty handling offers an attractive improvement for dynamic parameter adaptation in metaheuristic methods, and, in fact, the use of Interval Type-2 Fuzzy Inference Systems (IT2 FIS) has been shown to provide better results with respect to Type-1 Fuzzy Inference Systems (T1 FIS) in recent works. Based on the performance improvement exhibited by IT2 FIS, the present paper aims to implement the Shadowed Type-2 Fuzzy Inference System (ST2 FIS) for further improvements in dynamic parameter adaptation in Harmony Search and Differential Evolution optimization methods. The ST2 FIS is an approximation of General Type-2 Fuzzy Inference Systems (GT2 FIS), and is based on the principles of Shadowed Fuzzy Sets. The main reason for using ST2 FIS and not GT2 FIS is because the computational cost of GT2 FIS represents a time limitation in this application. The paper presents a comparison of the conventional methods with static parameters and the dynamic parameter adaptation based on ST2 FIS, and the approaches are compared in solving mathematical functions and in controller optimization.

Hybrid intelligent deep kernel incremental extreme learning machine based on differential evolution and multiple population grey wolf optimization methods

ABSTRACTFocussing on the problem that redundant nodes in the kernel incremental extreme learning machine (KI-ELM) which leads to ineffective iteration increase and reduce the learning efficiency, a novel improved hybrid intelligent deep kernel incremental extreme learning machine (HI-DKIELM) based on a hybrid intelligent algorithms and kernel incremental extreme learning machine is proposed. At first, hybrid intelligent algorithms are proposed based on differential evolution (DE) and multiple population grey wolf optimization (MPGWO) methods which used to optimize the hidden layer neuron parameters and then to determine the effective hidden layer neurons number. The learning efficiency of the algorithm is improved by reducing the network complexity. Then, we bring in the deep network structure to the kernel incremental extreme learning machine to extract the original input data layer by layer gradually. The experiment results show that the HI-DKIELM methods proposed in this paper with more compact network structure have higher prediction accuracy and better ability of generation compared with other ELM methods.

Application the differential evolution for solving the problem of minimizing the power shortage of electric power systems

Based on the experience of domestic and foreign researchers, it is known that there are various mathematical models, software systems, and optimization methods used to solve the set tasks for assessing the resource adequacy of electric power systems (EPS). However, the continuous development of EPS leads to the complication and integration of systems against the background of which it becomes necessary to take into account an increasing number of its elements and parameters in one task. Thus, for more effective (in terms of speed and accuracy) solutions of modified models, it is required to analyze and search the most appropriate set of optimization methods. In this connection, the purpose of this study is to analyze the applicability and the effectiveness of applying the method of differential evolution and gradient optimization methods for the model of minimizing the power deficit, which should be also compared. The article considers the analysis of the results of the work that optimization methods, studies were conducted on a test isolated EPS, with various tuning parameters. As a result, it was confirmed that these methods could be used to solve the problem. From the point of view of accuracy and resources expended on calculations, the most efficient among the implemented methods was the method of differential evolution, which was confirmed by numerical experiments on the small systems.