Differential Evolution Technique Research Articles

Application of Multi-Level Thresholding Fuzzy Entropy and Differential Evolution Techniques to Medical Image Compression

Each storage medium possesses a capacity that is vital to technological progress in supporting internet speed for downloading extensive data. Effective storage media management includes compressing image data to optimize available space utilization for efficient usage. Digital processing of image data for each patient over a specific duration is crucial. This study proposes medical image compression utilizing multi-level thresholding employing the fuzzy entropy and differential evolution (FE-DE) algorithms. The compression results are subsequently assessed using the Peak Signal to Ratio (PSNR), Structural Similarity Index Measure (SSIM), and Feature Similarity Index Measure (FSIM) to appraise the algorithm's performance and the quality of the compressed images. Employing Fuzzy Compression yields increasing PSNR, SSIM, and FSIM values as the threshold level rises, with the highest values achieved at threshold level 40. The increase in value is in line with the visual quality and compressed image produced.

Stock Market Prediction Using Machine Learning Techniques

The prediction of stock market prices holds significant importance within the contemporary economic landscape. Consequently, there has been a notable surge in scholarly interest directed towards exploring novel avenues for enhancing stock market prediction capabilities. Recent research endeavors have illuminated the potential predictive value inherent in various data streams, including historical stock data and user-generated content sourced from platforms such as Twitter and web news. These investigations have revealed a discernible relationship between social mood, as reflected in online discourse, and future stock price movements. However, prior studies have often overlooked the incorporation of such sentiment-derived information, thus presenting an information gap. In the present study, we address this gap by proposing an effective methodology for the integration and analysis of multiple information sources to facilitate more accurate stock price predictions. Leveraging Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) models, we conduct a comprehensive analysis of disparate data sources. Furthermore, we employ an ensemble approach, incorporating Weighted Average and Differential Evolution techniques, to refine the predictive accuracy of our models. Our findings demonstrate the efficacy of the proposed methodology in generating highly accurate stock price predictions across varying future time horizons, including one-day, seven-day, 15-day, and 30-day intervals. These predictions offer valuable insights for investors seeking to make informed decisions regarding their investment strategies and enable companies to gauge their anticipated performance within the stock market landscape.

Portfolio optimisation of international real estate investment trusts market during COVID-19: A behavioural perspective

This paper employs the cumulative prospect theory to investigate how deviation from rational investor asset selection improves portfolio optimisation. Firstly, asset portfolios are constructed by utilising the cumulative prospect theory, which captures investors’ psychology and risk tolerance and is herein referred to as a behavioural portfolio (BF). Secondly, the cluster technique is also used to build behavioural-centred investment portfolios that capture all the relevant moment properties of the asset return distribution as well as investors’ psychological dynamics and risk appetite, herein called the cluster moment behavioural portfolio (CMBF). The constructed portfolios are optimised by copula and differential evolution techniques. The analysis of optimisation of the constructed portfolios indicates that for behavioural portfolios (BF), in all phases of our sample period, portfolios with higher behavioural scores outperformed those with lower behavioural scores. And in the cluster moment behavioural portfolio (CMBP), for the pre-COVID and the COVID phases, the portfolios with lower behavioural scores outperform those with higher behavioural scores; however, for the full sample phase, the portfolio with a higher behavioural score outperforms the portfolio with the lower behavioural scores. The optimisation results of all the constructed portfolios largely favour portfolios with higher behavioural scores over those with lower scores. The results offer investment suggestions to guide investors with varying risk tolerance levels and those who deviate from the rational investor on how they can enhance their portfolio optimisation.

Bilevel planning of electric vehicle charging station and battery swapping station considering real-time uncertainty

The placement of electric vehicle charging stations (EVCS) and battery swapping stations (BSS) is crucial to meet demand while minimizing their impact on the power system network. This article addresses the placement and scheduling of EVCS and BSS within a radial distribution network (RDN) overlaid with a road network. Electric Vehicle Routing Problem (EVRP) and Traffic Assignment Problem (TAP) is introduced to reduce EV energy consumption during trips to EVCS and BSS. A Bi-layer optimization approach is used, with the outer layer minimizing energy loss by allocating EVCS and BSS optimally, and the inner layer optimizing scheduling considering associated costs. Uncertainties related to EV is considered on a real-time trip basis and modelled using 2m-Point estimation method. The problem is solved using Differential Evolution (DE) and Prairie Dog Optimization (PDO) techniques. PDO results in a 9.6% reduction in total energy losses and a 22.5% decrease in total associated costs by optimally placing EVCS at 69, 25,114 and BSS at 19, 84,113 of the RDN compared to DE. Inclusion of 2-m PEM uncertainty increases total energy loss by 8.76% but decreases total associated costs by 6.97% compared to real-time uncertainty cases, enhancing the realism of the results.

Alternative Strategies for Effective Utilization of Carbon Dioxide in Dimethyl Ether Synthesis

AbstractConverting CO2 into chemicals, e.g., methanol and dimethyl ether (DME), has been an attractive way to protect the global environment. In this process, the total catalyst volume of the methanol reactor was split into two sections to load the reactors. The catalyst volume of each reactor was optimized by the differential evolution technique. It was concluded that the indirect route yields a higher DME production rate than the direct one, as it produces higher amounts of methanol. CO2 conversions increased by 79 % in the indirect two‐stage process, which resulted in the highest DME production rate of 343 t per day. The results demonstrate how the concept of a two‐stage process in the indirect conversion of CO2 is feasible and beneficial for fuel production.

Placement of electric vehicle charging station and solar distributed generation in distribution system considering uncertainties

Electric vehicle penetration in the transport section is increasing and replacing the conventional fossil fuel based vehicles. Still, EV has not received success due to some limitations such as cost of the vehicle, battery capacity and availability of charging station. The availability of charging station depends on its geographical location. At the same time, location in the electrical network affects the energy loss and voltage deviation. Therefore, a road network of urban area overlapped with a 33-bus distribution network has been taken as test system for this work. Allocation of EV charging stations and photovoltaic energy resources as renewable distributed generation have been attempted simultaneously using 2-layer optimization. Differential Evolution and Harris Hawks Optimization techniques have been employed to solve the problem and the final results have been validated using eight other established optimization techniques. 2m point estimation method has been used to take care of uncertainties related to electric vehicles and PV. Monte-carlo simulation is also applied to cross verify the performance. The land cost, customer accessibility to charging station have been taken into account to allocate it at proper places. The whole work has been performed based on the 24-hrs dynamically varying electric vehicles flow and PV outputs.

Parameter extraction of solar photovoltaic models using queuing search optimization and differential evolution

Given the photovoltaic (PV) model’s multi-model and nonlinear properties, extracting its parameters is a difficult problem to solve. Furthermore, because of the features of the problem, the algorithms that are used to solve it are subject to becoming stuck in local optima. Nonetheless, proper estimation of the parameters is essential due to the large impact they have on the performance of the PV system in terms of current and energy production. Moreover, the majority of the previously proposed algorithms have satisfactory results for determining PV model parameters. However, for precision and robustness, they generally use a lot of computational resources, such as the quantity of fitness assessments. For alleviating the previous problems, in this paper, an improved queuing search optimization (QSO) algorithm dependent on the differential evolution (DE) technique and bound-constraint amendment procedure, which is called IQSODE, has been presented to efficiently extract the PV parameter values for various PV models. The DE algorithm is applied to each solution generated by the QSO algorithm in order to increase population diversity. IQSODE is tested against other state-of-the-art algorithms. The practical and statistical findings show that IQSODE outperforms other methods in extracting parameters from PV models such as single diode, double diode, and photovoltaic module models. Also, the performance of the proposed algorithm is assessed utilizing two practical manufacturer’s datasheets (TFST40 and MCSM55). Statistically, the IQSODE outperforms other state-of-the-art algorithms in terms of convergence speed, reliability, and accuracy. Thus, the presented method is deemed to be a viable solution for PV model parameter extraction.

DEICA: A differential evolution‐based improved clustering algorithm for IoT‐based heterogeneous wireless sensor networks

SummaryWith the evolution of technology, many modern applications like habitat monitoring, environmental monitoring, disaster prediction and management, and telehealth care have been proposed on wireless sensor networks (WSNs) with Internet of Things (IoT) integration. However, the performance of these networks is restricted because of the various constraints imposed due to the participating sensor nodes, such as nonreplaceable limited power units, constrained computation, and limited storage. Power limitation is the most severe among these restrictions. Hence, the researchers have sought schemes enabling energy‐efficient network operations as the most crucial issue. A metaheuristic clustering scheme is proposed here to address this problem, which employs the differential evolution (DE) technique as a tool. The proposed scheme achieves improved network performance via the formulation of load‐balanced clusters, resulting in a more scalable and adaptable network. The proposed scheme considers multiple parameters such as nodes' energy level, degree, proximity, and population for suitable network partitioning. Through various simulation results and experimentation, it establishes its efficacy over state‐of‐the‐art schemes in respect of load‐balanced cluster formation, improved network lifetime, network resource utilization, and network throughput. The proposed scheme ensures up to 57.69%, 33.16%, and 57.74% gains in network lifetime, energy utilization, and data packet delivery under varying network configurations. Besides providing the quantitative analysis, a detailed statistical analysis has also been performed that describes the acceptability of the proposed scheme under different network configurations.

Minimizing the Active Power Losses and Retaining the Voltage Profile of the Distribution System Using Soft Computing Techniques with DG Source

The motivation of this research is to curtail the active power losses in the radial distribution system. This paper proposes a novel voltage stability indicator to determine the optimum conductor sizes for various distribution lines and find the conductor stability limit. This work proposes a new BAT algorithm for finding the optimal switching configurations using reconfiguration, which is used to minimize the active power losses. The proposed BAT algorithm gives the optimal locations to place the required amount of DG sources to improve the stability and minimize the power losses and maintain the voltage profile of the systems. The proposed BAT algorithm has been executed with the MATLAB 2016 software and compared with the differential evolution technique for IEEE 33 bus, IEEE 69 bus, and Indian real time 62 bus systems. The test results are applied on different conductors, and the real power flow on the different conductors are mapped in the proposed method using the novel voltage stability indicator. The radial distribution system has lower power losses, best voltage profile, cost of saving the DG source, optimal placing of a suitable rating of the DG source, optimal location of the DG source, and cost of saving the DG source which were achieved in this work. In this research, the distributed load flow analysis is implemented to find the parameters by the forward-backward sweep algorithm. The minimum bus voltage 0.95 pu is virtual in all the conductors. The loss reduction in the DE for IEEE 33 bus has been reduced from 42.4% to 45.3% and the loss reduction in IEEE 69 bus from 36.2% to 38.8% and the real time 62 bus from 47.5% to 49.15%. The loss reduction in the BAT algorithm for IEEE 33 bus has been reduced from 38.46% to 45.3% and the loss reduction in IEEE 69 bus is from 32.2% to 38.8%. The Indian standard real time 62 bus has been reduced from 38.92% to 49.15%. The proposed results are compared with the DE and BAT algorithm. The proposed BAT algorithm is found to be more effectual in reducing voltage deviation (VD) and reducing the power losses in the system.

Experimental validation of machine-learning based spectral-spatial power evolution shaping using Raman amplifiers.

We experimentally validate a real-time machine learning framework, capable of controlling the pump power values of Raman amplifiers to shape the signal power evolution in two-dimensions (2D): frequency and fiber distance. In our setup, power values of four first-order counter-propagating pumps are optimized to achieve the desired 2D power profile. The pump power optimization framework includes a convolutional neural network (CNN) followed by differential evolution (DE) technique, applied online to the amplifier setup to automatically achieve the target 2D power profiles. The results on achievable 2D profiles show that the framework is able to guarantee very low maximum absolute error (MAE) (<0.5 dB) between the obtained and the target 2D profiles. Moreover, the framework is tested in a multi-objective design scenario where the goal is to achieve the 2D profiles with flat gain levels at the end of the span, jointly with minimum spectral excursion over the entire fiber length. In this case, the experimental results assert that for 2D profiles with the target flat gain levels, the DE obtains less than 1 dB maximum gain deviation, when the setup is not physically limited in the pump power values. The simulation results also prove that with enough pump power available, better gain deviation (less than 0.6 dB) for higher target gain levels is achievable.

Advanced biped gait generator using NARX-MLP neural model optimized by enhanced evolutionary algorithm

A novel biped walking pattern combining robust zero-moment-point ZMP technique and pre-determined foot-lifting value is proposed in this paper. The implementation of suggested approach contains following stages. Initially, a one-step ZMP curve for a small-sized humanoid is created using the 3rd-order interpolating equation, with pre-determined velocity responding the ZMP concept. The next step, biped gait planning is modeled as a non-linear MIMO plant including ten degree-of-freedom DOF. Then, the installation of a biped walking pattern generator (WPG) based on the new hybrid Neural-NARX model is completed. Eventually, the novel Enhanced Differential Evolution (EDE) technique is applied to optimally identify the weights of the hybrid Neural-NARX structure, for ensuring robust robot walking in terms of desired ZMP trajectories and pre-determined foot-lifting value. All case studies confirm that it is surely provide a biped WPG satisfying both of the effectiveness and high robustness. The verification of the newly proposed WPG is adequately tested via both simulation and experiment results.

Recovery of valeric acid using green solvents

AbstractIn this work, extraction of valeric acid (VA) using tri‐n‐butyl phosphate (TBP) as a reactive extractant was carried out. To reduce the toxic effects of the conventional diluents on microorganisms, non‐toxic and green edible sunflower and soybean oils were tried as the diluents. The high values of the distribution coefficient and extraction efficiency advocated to use them in the bio‐refinery industries. Moreover, it shows intensification of the recovery of VA using reactive extraction process. Sunflower oil appeared to be a better diluent than soybean oil. The complexation reaction stoichiometry (m and n) and equilibrium complexation reaction constant were estimated by using the differential evolution technique. In spite of the loading ratio being less than 0.5, the estimated m/n was found to be more than 1.0. The higher values of occurred due to the 9higher stability of the VA‐TBP complex in sunflower oil than in soybean oil. The stoichiometry of VA decreased with increasing TBP concentration. The complex concentration, , was found to be higher for soybean oil. It increased with temperature and initial VA concentration but remained invariant with TBP concentration. Due to the decreasing trend of with temperature, the complexation reaction became exothermic. The enthalpy changes due to mass transfer stipulated easier mixing of the phases in sunflower oil than in soybean oil.

Runge–Kutta–Nyström methods of eighth order for addressing Linear Inhomogeneous problems

Second order Linear Inhomogeneous Initial Value Problems with constant coefficients are considered here. Runge–Kutta–Nyström (RKN) methods are amongst the most effective for addressing these problems. For attaining a certain algebraic order of accuracy, we need to solve a reduced set of order conditions (in comparison with conventional RKN) with respect to the coefficients. Here, using a seven stages method we manage to solve these equations up to eighth order. Differential Evolution technique was used for achieving this. Thus, our main contribution is that we saved one stage since conventional eight order RKN methods use eight stages for advancing a step. This new method is combined at no cost with a fifth and third order companion formulas. As consequence, a triplet of orders 8(5)3 is given for estimating local errors and adjust effectively the step lengths. The new triplet of methods is applied to various relevant problems and is found to outperform standard RKN pairs from the literature.

Spectral and Spatial Power Evolution Design With Machine Learning-Enabled Raman Amplification

We present a machine learning (ML) framework for designing desired signal power profiles over the spectral and spatial domains in the fiber span. The proposed framework adjusts the Raman pump power values to obtain the desired two-dimensional (2D) profiles using a convolutional neural network (CNN) followed by the differential evolution (DE) technique. The CNN learns the mapping between the 2D profiles and their corresponding pump power values using a data-set generated by exciting the amplification setup. Nonetheless, its performance is not accurate for designing 2D profiles of practical interest, such as a 2D flat or a 2D symmetric (with respect to the middle point in distance). To adjust the pump power values more accurately, the DE fine-tunes the power values initialized by the CNN to design the proposed 2D profile with a lower cost value. In the fine-tuning process, the DE employs the direct amplification model which consists of 8 bidirectional propagating pumps, including 2 s-order and 6 first order, in an 80 km fiber span. We evaluate the framework to design broadband 2D flat and symmetric power profiles, as two goals for wavelength division multiplexing (WDM) system performing over the whole C-band. Results indicate the framework’s ability to achieve maximum power excursion of 2.81 dB for a 2D flat, and maximum asymmetry of 14% for a 2D symmetric profile.

Subsurface Modeling using Gravity and TDEM in Jiken, Blora Regency

Geophysics plays an essential role in imaging the subsurface condition of the earth. Gravity and time-domain electromagnetic method is geophysical method that can be used to visualize the subsurface condition. In this research, gravity and TDEM surveys have been carried out in Jiken, Blora Regency. Modeling technique is needed to obtain the subsurface model that bring information related to subsurface condition. Inversion modeling is applied separately to the gravity data and TDEM data, respectively. The density interface inversion modeling is used to gravity data.Subsurface condition is approached by three layers model with different density contrast values in each layer. In these schemes, the modeling process will determine the thickness for every layer. While for TDEM modeling,differential evolution technique is applied to model the TDEM data. The subsurface condition is approached by four layers model. In these schemes, the modeling process will determine the resistivity and thickness for every layer. Finally, the model obtained from gravity inversion modeling is integrated into the model from TDEM inversion data by overlaying the model.

Combining evolutionary optimization with finite element method for optimizing transmission-line tower

Metaheuristic evolutionary methods are powerful tools for solving non-linear, many dimensional optimisation problems. In this article, one of these methods is combined with finite element method for optimising truss like structure. The advantages of the combined method are presented through a real engineering task, optimisation of transmission line tower. The design of the latter can take a variety of shapes, so in the present case, only the lower part can be optimised. For optimisation, we use the adaptive differential evolution (SaDE) technique. The objective function of the optimisation is the mass of the structure. Finite element analysis is used to determine the stresses. The overall and local buckling constraints have also been considered.

Intelligent transformer tap controller for harmonic elimination in photovoltaic interfaced micro-grid network

The photovoltaic (PV) system is interfaced to the microgrid through an on-load tap changer (OLTC) transformer. Pulse width modulation (PWM) AC choppers are used to control these OLTC but create harmonics owing to their non-optimal firing angles. In this paper, Differential Evolution (DE) and Grey Wolf Optimizer (GWO) techniques are used for optimal control of an AC chopper to keep the harmonic distortion of voltage and current within limits. An IEEE-13 node network is adapted as a micro-grid with PV integration through transformers. The simulated results are validated by a laboratory set-up. A dSPACE experimental set-up is used for the real-time implementation of optimization algorithms. The results show that the DE gives firing angles that improve power quality, particularly a reduction in total harmonic distortion and improvement in the root mean square voltage profile. The research is particularly useful for the on-line power quality improvement in PV interfaced microgrid networks.

Optimal scheduling of storage device, renewable resources and hydrogen storage in combined heat and power microgrids in the presence plug-in hybrid electric vehicles and their charging demand

Microgrids have faced an increasing penetration rate of renewable energy resources (RERs), plug-in hybrid electric vehicles (PHEVs), combined heat and power (CHP), and storage systems. These elements need to be optimally scheduled so that the optimal operation of the microgrid is obtained. This study employs a novel random structure to optimally manage energy in microgrids which contain proton exchange membrane fuel cell-combined heat and power (PEMFC-CHP), RERs, PHEVs, as well as storage devices. The aim is to take into account the uncertainty of PHEVs and RERs models, in which Monte Carlo Simulation (MCS) is incorporated. The hydrogen storage strategy for PEMFC-CHP units is also used in this study, this strategy is considered by a mixed integer nonlinear programming (MINLP) problem. Moreover, smart charging plans are utilized to charger PHEVs. The objective function aims to maximize the market profit. This paper uses the modified adaptive differential evolution (MADE) technique for analyzing the optimal operation of the microgrid, where the intermittent behavior of uncertainty parameters is investigated. Differential evolution (DE) adopts an iteration-based strategy to enhance a candidate solution using a quality criterion and optimize the problem. Moreover, the algorithm is modified in order to enhance its search capability to be able to search and find local and global points. A conventional test system is implemented for verifying the efficiency of the suggested strategy and various planning durations are considered. A comparison is also made between this method and its counterparts for various situations and conditions.

Metaheuristic Load-Balancing-Based Clustering Technique in Wireless Sensor Networks

The resource-constrained nature of wireless sensor networks engenders the development of energy-efficient network operations. To mitigate the prime concern of developing an energy-efficient network, clustering of the nodes has emerged as a very effective tool. If executed intelligently, clustering can not only help in obtaining even load distribution among the network nodes but also help in having the enhanced network lifetime and scalability. In this work, a Metaheuristic Load-Balancing-Based Clustering Technique (MLBCT) in wireless sensor networks has been proposed which formulates the energy-balanced clusters based on the differential evolution technique to improve the network lifetime. To ensure the formation of balanced clusters, several metrics like nodes’ proximity, nodes’ distribution, and energy distribution across the sensing field have been considered. Moreover, to facilitate the even load distribution among the cluster members, a randomized rotation of cluster head is implemented. The supremacy of the proposed scheme is confirmed through an extensive set of simulations against the state-of-art schemes. Simulation results reflect an average gain of 51.85% in network lifetime under the variable network configurations in an ideal environment. Moreover, a thorough statistical analysis is performed to prove the efficacy of the proposed fitness function by obtaining confidence intervals under two different network scenarios with variable node counts.

Evaluation of thermal material properties based on SAW dispersion in the laser-induced dynamic subsurface temperature gradient

Dispersion of surface acoustic waves (SAWs) caused by a dynamic surface heating–cooling cycle has been applied for evaluation of thermal properties. A laser-generated broad-band SAW pulse is propagated through the material whose elastic properties and density were modified by the dynamic inhomogeneous temperature field produced by laser heating and subsequent cooling. A sample with depth-dependent material properties introduces a phase velocity dispersion in SAW propagation. Dispersion was measured by a differential technique, which helped to isolate the thermally induced dispersion and eliminate the contributions of other possible sources of dispersion. The dispersion curves were measured at several time instants, which allowed evaluation of the following parameters: thermal diffusivity, temperature dependence of the shear modulus, and the temperature magnitude. The inverse problem was solved by fitting the experimental dispersion curves into the theoretical ones by means of differential evolution techniques.