Modified Differential Evolution Research Articles

Innovative integrated workflow for data-driven production forecasting and well completion optimization: A Montney Formation case study

With the use of advanced data analytics and machine learning (ML) techniques, the oil and gas industry has transformed significantly in recent years. These innovations have opened new opportunities in reservoir engineering, allowing engineers to leverage data for better decision-making and well completion optimization. A key challenge in hydrocarbon exploration and production is forecasting gas production rates from unconventional sources. This is a crucial factor that affects how resources are allocated and decisions are made, requiring the application of novel techniques to enhance hydrocarbon production. Here, a novel and comprehensive automated workflow is introduced covering data collection, data preparation, feature selection, ML model development, and operational parameter optimization. The workflow uses various ML and optimization methods, including a modified Differential Evolution (MDE) algorithm, to improve gas production forecasting and optimize well completion parameters. We applied the proposed workflow to 3144 horizontal gas wells in the Montney Formation, British Columbia (BC), Canada, to assess its performance. The results showed the advantages of incorporating the initial 24 months of cumulative gas production data alongside well and completion data. Also, following the fine-tuning of hyperparameters for the ML algorithms, we identified the most effective model for forecasting cumulative gas production within the Montney Formation as a two-layer Artificial Neural Network (ANN) model. Moreover, using the MDE algorithm, the optimization results revealed the possibility of increasing gas production by more than 10% for about 47% of the wells. This research makes a significant contribution to the field of unconventional gas exploration by introducing an automated workflow that simplifies data processing, model development, and decision-making processes. It also offers valuable insights for optimizing unconventional gas production in the Montney Formation and similar reservoirs, as the energy industry moves towards more sustainable and efficient practices.

A metaheuristic algorithm for regulating virtual inertia of a standalone microgrid incorporating electric vehicles

AbstractModern electrical networks, particularly microgrids, have seen a sharp rise in acquiring non‐conventional sources. The inertia of the microgrid decreases drastically because RESs have been used in place of traditional synchronous generators. The reduced inertia negatively impacts the dynamics and performance of the microgrid with RESs, which decreases the microgrid's stability, especially in operation on an island. The primary purpose of this research study is to enhance the dynamic security of an island microgrid by merging an electric vehicle with a frequency control technique based on virtual inertia control. A Proportional Integral Derivative Filter Constant (PIDFN) controller optimally created using the Modified Differential Evolution (MDE) method served as the foundation for control in the virtual inertia control loop. The effectiveness of the MDE‐based PIDFN controller was examined considering the diverse operational scenarios are compared and contrasted with those of traditional methods Differential Evolution (DE) and Teaching Learning Based Optimization (TLBO)‐based PIDFN controllers. Real‐time wind and solar power statistics and random load fluctuations were incorporated to provide realistic simulation settings. The outcomes demonstrate that the MDE‐based PIDFN controller performs better in reference frequency tracking and reducing frequency disturbances than the other optimization strategies.

Optimizing municipal solid waste collection vehicle routing with a priority on infectious waste in a mountainous city landscape context

The growth of the economy, urban sprawl, and population expansion precipitate a substantial increase in solid waste generation, particularly in vital regions like the capital area and economically significant cities, including renowned tourist destinations. Furthermore, the protracted spread of the COVID-19 virus has led to a notable increase in the quantity of infectious waste. In this regard, the safe and effective management of municipal solid waste (MSW) collection and transportation emerges as a major concern in MSW management. This paper aims to determine routes for waste collection, both infectious and noninfectious, from waste collection points to diverse waste disposal sites in the mountainous Khao Kho district of Phetchabun province, located in northern Thailand, with the objective of minimizing total fuel consumption and service time. Fuel consumption is contingent upon both the distance traveled and the prevailing condition of the road. The road condition exerts an influence on the vehicle's speed, thereby directly impacting fuel efficiency. In the context of service time, priority is assigned to collection points with substantial quantities of infectious waste, given the imperative to promptly dispose of such waste to mitigate the risk of transmission. In this paper, a mixed-integer programming model and three modified differential evolution (MDE) algorithms were developed to solve the problem. The computational results reveal that the MDE outperformed the traditional DE and is effective for the MSW transportation management system.

A modified differential evolution algorithm for frequency management of interconnected hybrid renewable system

In recent decades, the insufficiency in power production has led to the incorporation of renewable energy sources into microgrid systems. However, ambiguity in the generation of renewable sources and load variation impacts on the system frequency influencing the stable operation of microgrid system. To augment the stable operation of the system an intelligent controller is required for continuous electric power. The implementation of a modified differential evolution (MDE)-based cascaded PIDFN controller using ITAE is proposed in this work. In order to demonstrate the robustness and efficacy of the proposed MDE optimization technique is compared with DE, TLBO, IWO and PSO.MDE-based cascaded PIDFN controller is implemented for governing the frequency in two-area interconnected microgrid system. The system is substantiated over load perturbations, system uncertainties, communication delay and real time data of solar irradiance and wind speed and action of UPFC in MATLAB<sup>®</sup>/SIMULINK environment.

Multi-criteria analysis of cell-recycle based continuous lactic acid production process

ABSTRACT This study focuses on the optimization of the cell-recycle based continuous lactic acid (LA) fermentation production process with the estimation of improved kinetic parameters. The non-dominated sorting genetic algorithm II (NSGA-II) is used considering seven variables and five imposed constraints for multi-objective optimization (MOO) study. Three objectives namely LA productivity, substrate conversion, and yield are formed for the maximization purpose. Three different cases are constructed by using a combination of two bi-objectives and one tri-objective optimization problem, and the modified differential evolution (MDE) algorithm is used to individually optimize each case. Pareto ranking is carried out for MOO, and the best optimal solution is determined using the technique for order preference by similarity to the ideal solution (TOPSIS) method. The highest value of volumetric productivity of LA (184.363 kg/m3.h) is reported in case-4a. The highest yield (1.176) is reported in case-2, while the highest substrate conversion (0.963) is reported in case-1.

One–dimensional magnetotelluric inversion by modified differential evolution algorithm

Traditional methods of solving geophysical inverse problems often used an initial structural model and an iterative process to find solutions. During each iteration, the model was linearized and updated, then the error between the model's response and the observed data were calculated and minimized. The inverse results solved by this method were often strongly dependent on the initial model choice, and the minimum of the objective function found could be the local value but not the global minimum. Global search methods such as genetic algorithm (GA) overcame these limitations of traditional solutions. This paper presented the application of modified differential evolution (MDE) algorithm which was developed from the genetic algorithm, to one-dimension (1D) magnetotelluric inversion. The algorithm had been used to invert two 3-layer geoelectrical models. The results showed that when using a 3-layer model for inversion, the obtained parameters of the subsurface almost coincided with those of the theoretical models. In the case the number of layers used for inversion had more than three layers (four layers and five layers), the obtained results showed that there was still a good agreement between the inverted structure and the theoretical model. Therefore, the algorithm was applied to one-dimensional (1D) inversion for data of one magnetotelluric station measured at Cu Chi district, Ho Chi Minh city. The results showed that the subsurface structure down to a depth of 16 km consisted of 3 layers: the top layer had a resistivity of 119 Ω.m with a thickness of about 760 m, the middle resistive layer with a resistivity of 4353 Ω.m with about 10 km thickness, and the lower half-space with a relatively low resistivity of 41.4 Ω.m. This result was consistent with the geoelectric structure information obtained from other magnetotelluric studies carried out in the studied area, demonstrating the practical applicability of the improved differential evolution algorithm.

Frequency Management of an Interconnected Power System using Modified Differential Evolution Algorithm

Frequency Management of an Interconnected Power System using Modified Differential Evolution Algorithm

Investigation of Mechanical and Tribological Characteristics of Medical Grade Ti6al4v Titanium Alloy in Addition with Corrosion Study for Wire EDM Process

Metals used in biomedical applications are frequently coated to prevent oxidation and metallic ion release, both of which can be harmful due to toxic effects. To prevent these adverse effects of metals, researchers have focused their efforts on developing various coating techniques, facilitating surface coating, or obtaining functional surfaces. (WEDM) is now considered a difficult method of obtaining functional surfaces for medical applications. The properties of the surface and subsurface layers obtained by the WEDM method are particularly interesting in this regard. The analysis utilised RSM-based computational technique to evaluate the WEDM characteristics (MRR SR) of Ti6Al4V Titanium Alloy in biomedical applications. The biggest drawback of the material in the biomedical industry, which includes orthopedic applications and dental implants, would be that it releases harmful atoms such as iron, chromium, and nickel into the bodily fluid environment. To combat the problems, a hydroxyapatite layer applied to the metal implant improves biocompatibility, osteocompatibility, and antimicrobial properties. By comparing the Modified Differential Evolution (MDE) approach to the basic differential evolution (DE) optimization strategy, the effectiveness of the MDE approach has been established. According to the cyclic polarized test, the Hap coated Titanium material had better corrosion resistance than the pure sample. The Hap coated titanium material has a higher zone of inhibition than the pure sample. The next step is to synthesis hydroxyapatite from cuttlebone, which is then electrodeposited onto titanium. FTIR, electrochemical tests, FESEM, and SEM were used to describe the coated sample, as well as an antibacterial test using E. Coli and B. Cereus bacteria. Because it is porous, the Hap coating helps bone tissue growth by preventing detrimental metal ions from escaping into the biological medium. The corrosion inhibition efficiency of the coated sample was performed in SBF (NaHCO3—0.35 g/L, MgCl2.6H2O—0.30 g/L, CaCl2·2H2O—0.37 g/L, K2HPO4. 3H2O—0.23 g/L, Na2SO4—0.071 g/L, NaCl—7.99 g/L, KCl—0.22 g/L, Tris’s buffer—6.063 g/L) solution using the potentiodynamic polarisation method and the solution pH was maintained.

Ensuring expected security cost with flexible resources using modified DE algorithm based dynamic optimal power flow

This paper presents a new approach to solve the Expected-Security-Cost with Dynamic Optimal Power Flow (ESCDOPF) problem incorporating flexible resources (FRs). The main objective of this approach is to minimize the expected total operation cost, which includes the overall system cost in both pre-and post-contingency states, by satisfying all the constraints of the model. The proposed model incorporates FRs such as game-theory based demand-response-management, battery-energy-storage-systems, and HVDC systems to reduce overall operating costs by ensuring adequate power balance and also maintaining the voltage and line loading limits. To solve the proposed model on an IEEE-30 bus system, a “Modified Differential Evolution” (MDE) algorithm is developed based on a combination of new crossover and new local adaptation approaches. This combination guarantees a good balance between exploration as well as extraction power with less computational costs and population size. The effectiveness of the proposed algorithm is tested for OPF, DOPF and ESCDOPF problems. From the results, it is observed that the proposed algorithm for the ESCDOPF problem helps to minimize the total system operation cost up to 3.04% in all scenarios when tested with/without FRs during pre-and post-contingency states.

Modified metaheuristic algorithms to design a closed-loop supply chain network considering quantity discount and fixed-charge transportation

Discount is an efficient way to reduce the closed-loop supply chain costs, and applying it would make the model closer to real ones. In this paper, the quantity discount is firstly applied along with fixed and variable transportation costs. The application of well-known, efficient algorithms, alongside developing modified versions to address the developed model is another contribution of this study. To calibrate the proposed algorithms’ parameters and operators, the Taguchi method is used. In this regard, several test problems in different sizes are generated considering the concerns of real-world cases, and the algorithms’ efficiencies are investigated by the relative percentage deviation method. The results show the superior performance of the hybrid algorithm of modified differential evolution and restart mechanism (MDE_Restart) and the algorithm of modified differential evolution (MDE) compared to the other employed algorithms.

Reactive power management by using a modified differential evolution algorithm

AbstractIn this article, a modified differential evolution (MDE) algorithm is proposed and applied to provide the solution for reactive power management by incorporating the flexible alternating current transmission systems (FACTS) controllers. The proper siting of FACTS controller has been achieved with an objective to minimize the losses and to improve the loading capability. The power flow analysis is performed to determine the optimal position for FACTS controllers. These controllers are incorporated in the most heavily loaded lines and hence controls the power flow in that particular line and allow more power to be transmitted in the remaining lines. The proposed MDE algorithm uses a novel DE/best3/1/bin mutation operator to produce three temporary mutant vectors which are averaged to obtain the mutant vector. Hence, the decision vectors of a generation simultaneously move toward the three best decision vectors of the population thereby maintains a better trade between exploration and exploitation. The proposed MDE algorithm is applied on different standard test bus (i.e., IEEE30, IEEE57, and IEEE118) systems with varying active and reactive loading (i.e., 100%, 110%, and 120%). The proposed method's performance is compared to those obtained from some well‐known meta‐heuristic algorithms. The proposed MDE algorithm optimized FACTS controllers reduce transmission loss by 60.90% in IEEE30 bus, 49.72% in IEEE57 bus and 8.37% in IEEE118 bus test system under base loading. The statistical analysis of the obtained results is carried out using the Wilcoxon signed rank test and the Friedman and Nemenyi hypothesis test, which ensures the reliability and robustness of the proposed method.

Performance optimization of differential evolution with slime mould algorithm for multilevel breast cancer image segmentation

Breast cancer is one of the most dangerous diseases for women's health, and it is imperative to provide the necessary diagnostic assistance for it. The medical image processing technology is one of the most critical of all complementary diagnostic technologies. Image segmentation is the core step of image processing, where multilevel image segmentation is considered one of the most efficient and straightforward methods. Many multilevel image segmentation methods based on evolutionary and population-based methods have been proposed in recent years, but many have the fatal weakness of poor convergence accuracy and the tendency to fall into local optimum. Therefore, to overcome these weaknesses, this paper proposes a modified differential evolution (MDE) algorithm with a vision based on the slime mould foraging behavior, where the recently proposed slime mould algorithm (SMA) inspires it. Besides, to obtain high-quality breast cancer image segmentation results, this paper also develops an excellent MDE-based multilevel image segmentation model, the core of which is based on non-local means 2D histogram and 2D Kapur's entropy. To effectively validate the performance of the proposed method, a comparison experiment between MDE and its similar algorithms was first carried out on IEEE CEC 2014. Then, an initial validation of the MDE-based multilevel image segmentation model was performed by utilizing a reference image set. Finally, the MDE-based multilevel image segmentation model was compared with peers using breast invasive ductal carcinoma images. A series of experimental results have proved that MDE is an evolutionary algorithm with high convergence accuracy and the ability to jump out of the local optimum, as well as effectively demonstrated that the developed model is a high-quality segmentation method that can provide practical support for further research of breast invasive ductal carcinoma pathological image processing.

Novel approach to find the optimal parameters of a tractor disc plough used for land preparation

This study presents a new approach to find the optimal operating parameters of a tractor disc plough, to minimize the fuel used for the land preparation of sugarcane fields. The new approach is composed of three steps: (1) construct the regression model; (2) use modified differential evolution (MDE) to find the optimal parameters; and (3) verify the optimal parameters by performing a real experiment. The use of MDE obtained optimal parameters giving 12.37% and 16.96% lower fuel use than for the traditional method, when using the response optimizer and particle swarm optimization, respectively.

Feature extraction and power quality event classification using Curvelet transform and optimized extreme learning machine

This article presents an efficient method for power quality events (PQEs) detection and classification based on Curvelet transform (CT) and optimized extreme learning machine (OELM). Initially, various PQEs signal data are extracted even under noisy and simultaneously occurred multi-event conditions to reflect the real-time conditions. Relevant features of all these extracted signals are computed by using a multi-resolution and multidirectional fast discrete CT (FDCT) approach. These features are used to classify the events accurately by the proposed OELM. In this classification strategy, a modified differential evolution (MDE) is introduced to optimize the conventional ELM to enhance its precision rate. The proposed novel approach is tested and analyzed under various noisy conditions with 20 dB, 30 dB, and 50 dB with single and multi PQEs conditions. Comparative results with other recently proposed approaches by various authors reveal that the proposed CT- and OELM-based classifier titled CT-OELM can be considered as a competitive choice for implementing in the real-time monitoring system.

Modified Differential Evolution Algorithm for Time-Modulated Linear Array Antenna

A modified differential evolution (MDE) algorithm based on a novel mutation strategy and adaptive adjustment strategy of parameter crossover rate (CR) is proposed to improve the population diversity and to avoid frapping in local optima. Also the simplified quadratic interpolation is employed to accelerate the convergence rate. Benchmark functions have been provided to verify the MDE algorithm. Compared with other improved evolutionary algorithms, experiment results reveal that the MDE has a promising performance in the convergence rate and the exploration ability. Finally, the proposed algorithm is proved to realize accelerating the optimization of time-modulated arrays (TMA).

Optimization of digital predistortion models for RF power amplifiers using a modified differential evolution algorithm

This paper, investigates and presents the optimal parameter identification of digital pre-distortion (DPD) models for radio frequency power amplifiers (RF PAs) using a modified differential evolution (MDE) based optimization algorithm. Compared to the conventional exhaustive search method which is computationally intensive, our proposed approach enables the identification of a best-fit DPD model from a combinatorially large model space in a short time. In addition, applying information criteria based objective functions in the optimization process enables us to achieve sparse selection of dynamical models, which balances the model accuracy and model complexity. Experimental validation on a GaN based class AB power amplifier illustrates that, our proposed approach was able to accurately identify complexity reduced optimal DPD models without compromising the modeling accuracy.

RETRACTED ARTICLE: Estimation of loadability limit with N-1 and N-2 outages using evolutionary computation techniques

Voltage stability primarily depends on the voltage magnitude, phase angle, real and reactive power constraint of the electric power system. Even during emergencies like contingency (outages), the stability of the electric power structure will be enhanced by improving the Loadability Limit (LL) of the transmission sector. Flexibility in the real and reactive power flow in the transmission system is achieved by the Flexible AC Transmission System (FACTS) devices. These devices can be placed anywhere in the transmission sector. To get effective control over the power flow through the transmission lines and to achieve the maximum loadability with the minimal installation cost, optimal choice and placement of FACTS devices are essential. In this manuscript, efforts had been taken to analyze the LL with outages for hybrid electric power structures. The proposed method is simulated and tested with the hybrid version of standard IEEE 30 bus system. Three types of FACTS devices like Thyristor Controlled Series Capacitor (TCSC), Static VAr Compensator (SVC) and Unified Power Flow Controller (UPFC) are efficiently selected and placed in the transmission lines. For the optimal positioning and placement of these devices, the Contingency Severity Index (CSI) and Fast Voltage Stability Index (FVSI) have been used. Differential Evolution (DE) and Modified Differential Evolution (MDE) algorithms are applied to optimize the obtained results. DE is an evolutionary search based soft computing algorithm popularly handed to resolve multifarious problems. MDE is the enhanced version of DE that embraces a prior knowledge about the solution space at every stage of the search. The main focus of this work is (i) to identify the weak branches and buses in the system using CSI and FVSI. (ii) to optimize the number, location and settings of FACTS devices using various soft computing techniques like DE and MDE. (iii) to evaluate ML of a transmission system with FACTS devices under normal and contingency conditions using DE and MDE. (iv) to calculate the cost required for the installation of FACTS devices. (v) to enhance ML of pool and hybrid model of deregulated electric power market with contingency using the optimal number, rating and positioning of FACTS devices.

Machinability Analysis and Optimization in Wire EDM of Medical Grade NiTiNOL Memory Alloy.

NiTiNOL (Nickel–Titanium) shape memory alloys (SMAs) are ideal replacements for titanium alloys used in bio-medical applications because of their superior properties like shape memory and super elasticity. The machining of NiTiNOL alloy is challenging, as it is a difficult to cut material. Hence, in the current research the experimental studies on machinability aspects of medical grade NiTiNOL SMA during wire electric discharge machining (WEDM) using zinc coated brass wire as electrode material have been carried out. Pulse time (Ton), pause time (Toff), wire feed (WF), and servo voltage (SV) are chosen as varying input process variables and the effects of their combinational values on output responses such as surface roughness (SR), material removal rate (MRR), and tool wear rate (TWR) are studied through response surface methodology (RSM) based developed models. Modified differential evolution (MDE) optimization technique has been developed and the convergence curve of the same has been compared with the results of differential evolution (DE) technique. Scanning electron microscopy (SEM) and energy dispersive X-ray spectrography (EDS) analysis are carried out to study the surface morphology of the machined alloy. SV is found to be more influential process parameter for achieving better MRR with minimal SR and TWR, followed by Ton, Toff, and WF. The WF has good impact on reduced SR and TWR responses and found to be least significant in maximizing MRR.

Parameter optimization of software reliability models using improved differential evolution algorithm

Differential evolution (DE) is known as a strong and simple optimization method able to work with non-differential, nonlinear, and multimodal functions. This paper proposes a modified differential evolution (MDE) algorithm for solving a high dimensional nonlinear optimization problem. The issue is finding maximum likelihood estimation (MLE) for the parameters of a non-homogeneous Poisson process (NHPP) software reliability model. We make two modifications to DE: a mutation scheme based on a new affine combination of three points for increasing the exploration power of the algorithm, and another is a uniform scaling crossover scheme to increase the exploitation ability of the algorithm. The performance of the proposed scheme is empirically validated using five software reliability models on three software failure datasets. Analysis of research findings indicates that the proposed scheme enhances the convergence speed of the DE algorithm, and preserves the quality of the solution. A comparison with two other peer algorithms is also shown the superiority of the proposed algorithm.

Estimation and Correction of Sampling Time Offsets in Tiadcs using Optimization Algorithm

In recent communication technologies, very high sampling rates are required for rf signals particularly for signals coming under ultra high frequency (UHF), super high frequency (SHF) and extremely high frequency (EHF) ranges. The applications include global positioning system (GPS), satellite communication, radar, radio astronomy, 5G mobile phones etc. Such high sampling rates can be accomplished with time-interleaved analog to digital converters (TIADCs). However, sampling time offsets existing in TIADCs produce non-uniform samples. This poses a drawback in the reconstruction of the signal. The current paper addresses this drawback and offers a solution for improved signal reconstruction by estimation and correction of the offsets. A modified differential evolution (MDE) algorithm, which is an optimization algorithm, is used for estimating the sampling time offsets and the estimated offsets are used for correction. The estimation algorithm is implemented on an FPGA board and correction is implemented using MATLAB. The power consumption of FPGA for implementation is 57mW. IO utilization is 27% for 4-channel TIADCs and 13% for 2-channel TIADCs. The algorithm estimated the sampling time offsets precisely. For estimation the algorithm uses a sinusoidal signal as a test signal. Correction is performed with sinusoidal and speech signals as inputs for TIADCs. Performance metrics used for evaluating the algorithm are SNR (signal to noise ratio), SNDR (signal to noise and distortion ratio), SFDR (spurious-free dynamic range) and PSNR (peak signal to noise ratio). A noteworthy improvement is observed in the above mentioned parameters. Results are compared with the existing state of the art algorithms and superiority of the proposed algorithm is verified.