Quasi-oppositional Learning Research Articles

An improved whale algorithm for real-time boundary processing and its convergence analysis

Abstract To tackle the deficiencies in the whale algorithm, including its weak stability, sluggish convergence rate, and tendency to get trapped in local optima, an adapted whale optimization algorithm has been created, which introduces quasi-opposition learning and a real-time boundary processing mechanism. In the enhanced algorithm, a quasi-opposition learning mechanism is implemented to broaden the search scope and augment the variety of the population during the initial phases of iteration. This approach also helps to guarantee the convergence of the algorithm in the later phases of iteration. The unified boundary processing method of delay concentration is improved to solve the problem that a large amount of convergence damages diversity if a large number of transgressive individuals are unified and centralized. The algorithm flow is given and the asymptotic fitness and the asymptotic global optimal solution are proved. The time complexity is analyzed theoretically. Ultimately, six recognized algorithms were utilized to simulate the CEC 2017 function set across different scales. Findings indicate that the enhanced algorithm significantly boosts convergence rate, optimization precision, and solution robustness, demonstrating strong convergence characteristics.

Artificial neural network infused quasi oppositional learning partial reinforcement algorithm for structural design optimization of vehicle suspension components

Abstract This paper introduces and investigates an enhanced Partial Reinforcement Optimization Algorithm (E-PROA), a novel evolutionary algorithm inspired by partial reinforcement theory to efficiently solve complex engineering optimization problems. The proposed algorithm combines the Partial Reinforcement Optimization Algorithm (PROA) with a quasi-oppositional learning approach to improve the performance of the pure PROA. The E-PROA was applied to five distinct engineering design components: speed reducer design, step-cone pulley weight optimization, economic optimization of cantilever beams, coupling with bolted rim optimization, and vehicle suspension arm optimization problems. An artificial neural network as a metamodeling approach is used to obtain equations for shape optimization. Comparative analyses with other benchmark algorithms, such as the ship rescue optimization algorithm, mountain gazelle optimizer, and cheetah optimization algorithm, demonstrated the superior performance of E-PROA in terms of convergence rate, solution quality, and computational efficiency. The results indicate that E-PROA holds excellent promise as a technique for addressing complex engineering optimization problems.

Enhanced Target Localization in the Internet of Underwater Things through Quantum-Behaved Metaheuristic Optimization with Multi-Strategy Integration

Underwater localization is considered a critical technique in the Internet of Underwater Things (IoUTs). However, acquiring accurate location information is challenging due to the heterogeneous underwater environment and the hostile propagation of acoustic signals, especially when using received signal strength (RSS)-based techniques. Additionally, most current solutions rely on strict mathematical expressions, which limits their effectiveness in certain scenarios. To address these challenges, this study develops a quantum-behaved meta-heuristic algorithm, called quantum enhanced Harris hawks optimization (QEHHO), to solve the localization problem without requiring strict mathematical assumptions. The algorithm builds on the original Harris hawks optimization (HHO) by integrating four strategies into various phases to avoid local minima. The initiation phase incorporates good point set theory and quantum computing to enhance the population quality, while a random nonlinear technique is introduced in the transition phase to expand the exploration region in the early stages. A correction mechanism and exploration enhancement combining the slime mold algorithm (SMA) and quasi-oppositional learning (QOL) are further developed to find an optimal solution. Furthermore, the RSS-based Cramér–Raolower bound (CRLB) is derived to evaluate the effectiveness of QEHHO. Simulation results demonstrate the superior performance of QEHHO under various conditions compared to other state-of-the-art closed-form-expression- and meta-heuristic-based solutions.

Improving PID Controller Performance in Nonlinear Oscillatory Automatic Generation Control Systems Using a Multi-objective Marine Predator Algorithm with Enhanced Diversity

Power systems are pivotal in providing sustainable energy across various sectors. However, optimizing their performance to meet modern demands remains a significant challenge. This paper introduces an innovative strategy to improve the optimization of PID controllers within nonlinear oscillatory Automatic Generation Control (AGC) systems, essential for the stability of power systems. Our approach aims to reduce the integrated time squared error, the integrated time absolute error, and the rate of change in deviation, facilitating faster convergence, diminished overshoot, and decreased oscillations. By incorporating the spiral model from the Whale Optimization Algorithm (WOA) into the Multi-Objective Marine Predator Algorithm (MOMPA), our method effectively broadens the diversity of solution sets and finely tunes the balance between exploration and exploitation strategies. Furthermore, the QQSMOMPA framework integrates quasi-oppositional learning and Q-learning to overcome local optima, thereby generating optimal Pareto solutions. When applied to nonlinear AGC systems featuring governor dead zones, the PID controllers optimized by QQSMOMPA not only achieve 14%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} reduction in the frequency settling time but also exhibit robustness against uncertainties in load disturbance inputs.

Enhanced Gaussian Bare-Bone Imperialist Competition Algorithm Based on Doubling Sampling and Quasi-oppositional Learning for Global Optimization

Gaussian bare-bone imperialist competitive algorithm (GBB-ICA) is an effective variant of imperialist competitive algorithm (ICA), which updates the position of colonies by sampling a Gaussian distribution. However, the mean and standard deviation adopted by GBB-ICA is calculated only using the positions of imperialist and the colony itself, making the searching tends to trap into local optimum. To overcome this drawback, a new double Gaussian sampling strategy is proposed in this paper. An extra Gaussian sampling point, whose mean and standard is calculated using the positions of the second best colony and the current colony itself, is introduced into GBB-ICA. To further speed up the convergence and explore informative region, the quasi-oppositional learning technique is incorporated into GBB-ICA to produce more potential candidates in the assimilation step as well as generating a higher quality initial population. The proposed algorithm is called quasi-oppositional learning-based double Gaussian sampling bare-bone imperialist competitive algorithm (QOLBDGSBB-ICA) and is tested on 20 benchmark functions and four engineering design problems. Experimental results show that the proposed algorithm outperforms over other referenced ICA variants on 19 benchmark functions, which well validates the effectiveness of the proposed algorithm.

A novel reinforcement learning based Heap-based optimizer

The Heap-Based Optimization (HBO), a novel meta-heuristic algorithm, constructs a hierarchical heap resembling a company structure to facilitate interaction among search agents. This enables the search agent to learn various levels of information from the population to obtain improved solutions, but it has drawbacks such as limited search capability and slow convergence speed when tackling complex optimization problems. To address these challenges, we propose an enhanced heap optimizer based on reinforcement learning(RLHBO), which demonstrates robust stability, rapid convergence, and high solution accuracy. Firstly, fixed operators are replaced with a reinforcement learning dynamic control search strategy in RLHBO to regulate the search range of agents. This prevents agents from being restricted in their search when encountering local or global optima, thus enhancing their search capability. Additionally, RLHBO introduces a dimensional self-learning strategy and a convergence strategy based on search direction similarity to address issues such as invalid and discrete solutions, accelerating convergence. Furthermore, an initialization strategy based on quasi-oppositional learning is employed to increase the diversity of the algorithm-generated population, surpassing the limitations of random initialization and further boosting convergence speed. Extensive testing on various complex functions from CEC2017 and CEC2022 demonstrates that RLHBO, as presented in this paper, outperforms HBO and numerous other advanced MAs in terms of search capability and convergence speed.

Performance evaluation of linear antenna array using quasi opposition modified particle swarm algorithm

Linear antenna arrays find extensive application in the communication systems of the future, including IoT, 5 G, and beamforming technologies. However, sustaining subsidiary lobes while keeping a tight beamwidth remains a challenge. In this paper, an enhanced version of Artificial Hummingbird Algorithm (AHOA) is presented. AHOA is a kind of particle swarm algorithm based on the unique flying abilities and clever foraging techniques of hummingbirds seen in nature. In this research, a hybridization of AHOA and quasi opposition based learning is presented for linear antenna array applications. The quasi opposition learning based artificial hummingbird method has been developed to produce more accurate outcomes for further complicated tasks and is named as Quasi Opposition Based Artificial Hummingbird Algorithm. The approach is evaluated across various communication needs of the linear array, and the results are compared with those obtained from other conventional methods. In comparison to the other approach, the proposed strategy delivers the lowest subsidiary lobes along with the narrow beamwidth without any grating lobes. Thus, the proposed approach is capable of managing diverse linear array applications without sacrificing beamwidth or subsidiary lobes levels.

Optimization of CNN using modified Honey Badger Algorithm for Sleep Apnea detection

Sleep Apnea (SA) is the most prevalent breathing sleep problem, and if left untreated, it can lead to catastrophic neurological and cardiovascular illnesses. Conventionally, polysomnography (PSG) is used to diagnose SA. Nonetheless, this approach necessitates several electrodes, cables, and a professional to oversee the experiment. A promising alternative is using a single-channel signal for SA diagnosis, with the electrocardiogram (ECG) signal being among the most relevant and easily recordable. Recently, a convolutional neural network (CNN) has been used to extract efficient features from training data instead of manually selecting characteristics from ECG. However, selecting the best hyperparameter values for CNN can be challenging due to the vast number of possibilities. To address this, we propose a modified Honey Badger Algorithm (MHBA) combined with three improvement initiatives: quasi-opposition learning, arbitrary weighting agent, and adaptive mutation method. Our approach is evaluated on the Physionet Apnea ECG database, consisting of 70 single-lead ECG recordings annotated by qualified medical professionals. The experiments show that the MHBA outperforms traditional CNN and machine learning methods with an accuracy of 91.3%, AUC of 97.5%, specificity of 93.6%, and sensitivity of 90.1%. Our results demonstrate the effectiveness of the MHBA for SA detection.

A quasi-oppositional learning of updating quantum state and Q-learning based on the dung beetle algorithm for global optimization

There are many tricky optimization problems in real life, and metaheuristic algorithms are the most effective way to solve optimization problems at a lower cost. The dung beetle optimization algorithm (DBO) is a more innovative algorithm proposed in 2022, which is affected by the action of dung beetles such as ball rolling, foraging, and reproduction. Therefore, A dung beetle optimization algorithm is proposed based on quasi-oppositional learning and Q-learning (QOLDBO). First, the quantum state update idea is cleverly integrated into quasi-oppositional learning to increase the randomness of the generated population. And the best behavior pattern is selected by adding Q-learning in the rolling stage to improve the search effect. In addition, the variable spiral local domain method is proposed to make up for the shortage of developing only around the neighborhood optimum. For the optimal solution of each iteration, the dimensional adaptive Gaussian variation is selected and the optimal solution is retained. Experimental performance tests show that QOLDBO performs well in both benchmark test functions and CEC 2017. Simultaneously, the validity of the algorithm is verified on several classical practical application engineering problems.

A New Approach for Seepage Parameters Inversion Analysis Using Improved Whale Optimization Algorithm and Support Vector Regression

Seepage is the primary cause of dam failures. Conducting regular seepage analysis for dams can effectively prevent accidents from occurring. Accurate and rapid determination of seepage parameters is a prerequisite for seepage calculation in hydraulic engineering. The Whale Optimization Algorithm (WOA) was combined with Support Vector Regression (SVR) to invert the hydraulic conductivity. The good point set initialization method, a cosine-based nonlinear convergence factor, the Levy flight strategy, and the Quasi-oppositional learning strategy were employed to improve WOA. The effectiveness and practicality of Improved Whale Optimization Algorithm (IWOA) were evaluated via numerical experiments. As a case study, the seepage parameters of the Dono Dam located on the Baishui River in China were inversed, adopting the proposed inversion model. The calculated seepage field was reasonable, and the relative error between the simulated head and the measured value at each monitoring point was within 2%. This new inversion method is more feasible and accurate than the existing hydraulic conductivity estimation methods.

Optimized Back Propagation Neural Network Using Quasi-Oppositional Learning-Based African Vulture Optimization Algorithm for Data Fusion in Wireless Sensor Networks.

A Wireless Sensor Network (WSN) is a group of autonomous sensors geographically distributed for environmental monitoring and tracking purposes. Since the sensors in the WSN have limited battery capacity, the energy efficiency is considered a challenging task because of redundant data transmission and inappropriate routing paths. In this research, a Quasi-Oppositional Learning (QOL)-based African Vulture Optimization Algorithm (AVOA), referred to as QAVOA, is proposed for an effective data fusion and cluster-based routing in a WSN. The QAVOA-based Back Propagation Neural Network (BPNN) is developed to optimize the weights and threshold coefficients for removing the redundant information and decreasing the amount of transmitted data over the network. Moreover, the QAVOA-based optimal Cluster Head Node (CHN) selection and route discovery are carried out for performing reliable data transmission. An elimination of redundant data during data fusion and optimum shortest path discovery using the proposed QAVOA-BPNN is used to minimize the energy usage of the nodes, which helps to increase the life expectancy. The QAVOA-BPNN is analyzed by using the energy consumption, life expectancy, throughput, End to End Delay (EED), Packet Delivery Ratio (PDR) and Packet Loss Ratio (PLR). The existing approaches such as Cross-Layer-based Harris-Hawks-Optimization (CL-HHO) and Improved Sparrow Search using Differential Evolution (ISSDE) are used to evaluate the QAVOA-BPNN method. The life expectancy of QAVOA-BPNN for 500 nodes is 4820 rounds, which is high when compared to the CL-HHO and ISSDE.

Optimum Generation Scheduling of Thermal and Hydro Power System with Renewable Power Sources Using Enhanced Grey Wolf Optimization Algorithm

In this work, an algorithm of enhanced grey wolf optimization (EGWO) is developed to resolve the scheduling problem of a power system, which is having thermal, hydro, wind, and solar power plants with a battery energy storing system (BESS). The planning period covers 24 equal intervals of a day. In this scheduling problem, the impact on valve point loading of thermal plants, the time coupling effect in cascaded reservoirs of hydro units, and various constraints imposed on the power network are taken into consideration. The grey wolf optimization (GWO) technique is used, which is framed on the group attitude of grey wolves such as governance ranking and hunting activity. In this proposed algorithm, GWO algorithm is enhanced using three techniques. First, the quasi-oppositional learning approach is exploited to obtain the optimal solution quickly. Second, the elite mutation operator is applied to maximize the diversity of the swarm. Finally, by implementing the elastic-ball strategy, infeasible solutions are modified into feasible one. The potential of the EGWO technique is ascertained by employing it in two experimental settings. From the simulation outcome, it is inferred that the implemented technique bestows less operating cost with minimal computation time as compared to other evolutionary techniques.

Kernel semi-parametric model improvement based on quasi-oppositional learning pelican optimization algorithm

Statistical modeling is essential in many scientific research areas because it explains the relationship between the response variable of interest and a number of explanatory variables. However, it is not easy to determine the optimal model beforehand. Therefore, in this paper, we look at how to choose a hyper-parameter in a kernel semi-parametric regression model. A quasi-oppositional learning pelican optimization algorithm strategy is used to select the smoothness parameter. In comparison to other competitor approaches, simulation results revealed that the suggested method, the quasi-oppositional learning pelican optimization algorithm, is superior in terms of MSE. The experimental findings and statistical analysis show that when compared to the CV and GCV, our proposed quasi-oppositional learning pelican optimization algorithm provides greater performance in terms of computational time.

Quasi-Oppositional African Vultures Optimization-Based PIλDn Plus PIλ Controller for Frequency Control of an Interlinked Hybrid Power System

One of the challenging tasks in a hybrid power system is to provide an effective control strategy to attenuate frequency and power deviations that occur due to the intermittency of renewable energy resources (RERs) and load demand. To address this issue, we present a novel proportional fractional-order integral derivative filter plus proportional fractional-order integral (PIλDn plus PIλ) controller, which is applied for the load frequency control (LFC) operation of an interlinked hybrid thermal power system. Using quasi-oppositional learning, we also propose the maiden quasi-oppositional African vultures optimization algorithm (QOAVOA), which is used to tune the proposed controller by minimizing the objective function. First, the capability of the proposed QOAVOA tuned PIλDn plus PIλ controller is examined with a two-area thermal power system under load uncertainty and the performance is compared with the results of various optimization-based classical/fuzzy controllers. The sensitivity study is also performed to validate the robustness of the proposed control approach for handling systems’ parametric uncertainties. The suggested LFC mechanism is further validated on a two-area-hybrid thermal power system (2A-hTPS) comprising RERs and distributed generation sources to authenticate the tuning ability of the proposed optimization approach. The dynamic performance of considered 2A-hTPS with the suggested control approach is examined considering various scenarios such as changing load demand, uncertain wind perturbation, and random multi-step load perturbations of the wind turbine generator. The comparative dynamic performance of the suggested controller reveals its superiority over other controllers in terms of transient and steady-state responses. Finally, a few non-linearities are introduced to the test system, and the simulation study with non-linearities validates the potency of the proposed controller.

A Novel Quasi-Oppositional Learning-Based Chaos-Assisted Sine Cosine Algorithm for Hybrid Energy Integrated Dynamic Economic Emission Dispatch

In the current era of industrialization, renewable energy (such as wind and solar energy) plays an significant role in power generation sector, and it helps to decrease the generation cost and the environmental pollution. In this work, hybrid source of energy (like solar and wind energy) has been integrated with the traditional dynamic economic emission dispatch (EED) (DEED) problem to formulate a new model, i.e., complicated constrained hybrid energy integrated DEED problem, which may be able to generate less polluted power than the traditional DEED problem. Here, the quasi-opposition learning (QOL) approach and chaotic dynamics have been introduced in a novel sine cosine algorithm (SCA) to enhance its convergence and diversity. Effectiveness of the presented solution of the dynamic thermal-wind-solar EED problem has been properly validated by solving three aspects, i.e., the cost, the emission and the combined cost-emission using QOL-based chaotic SCA. The use of solar and wind energy in the DEED problem reduces the generating costs by 8% and 20.84%, respectively, compared to traditional and wind-integrated DEED. The robustness of the proposed modified SCA has been presented by comparing the results with the results offered by SCA and other recently published algorithms.

EJS: Multi-Strategy Enhanced Jellyfish Search Algorithm for Engineering Applications

The jellyfish search (JS) algorithm impersonates the foraging behavior of jellyfish in the ocean. It is a newly developed metaheuristic algorithm that solves complex and real-world optimization problems. The global exploration capability and robustness of the JS algorithm are strong, but the JS algorithm still has significant development space for solving complex optimization problems with high dimensions and multiple local optima. Therefore, in this study, an enhanced jellyfish search (EJS) algorithm is developed, and three improvements are made: (i) By adding a sine and cosine learning factors strategy, the jellyfish can learn from both random individuals and the best individual during Type B motion in the swarm to enhance optimization capability and accelerate convergence speed. (ii) By adding a local escape operator, the algorithm can skip the trap of local optimization, and thereby, can enhance the exploitation ability of the JS algorithm. (iii) By applying an opposition-based learning and quasi-opposition learning strategy, the population distribution is increased, strengthened, and more diversified, and better individuals are selected from the present and the new opposition solution to participate in the next iteration, which can enhance the solution’s quality, meanwhile, convergence speed is faster and the algorithm’s precision is increased. In addition, the performance of the developed EJS algorithm was compared with those of the incomplete improved algorithms, and some previously outstanding and advanced methods were evaluated on the CEC2019 test set as well as six examples of real engineering cases. The results demonstrate that the EJS algorithm can skip the trap of local optimization, can enhance the solution’s quality, and can increase the calculation speed. In addition, the practical engineering applications of the EJS algorithm also verify its superiority and effectiveness in solving both constrained and unconstrained optimization problems, and therefore, suggests future possible applications for solving such optimization problems.

IEGQO-AOA: Information-Exchanged Gaussian Arithmetic Optimization Algorithm with Quasi-opposition learning

Arithmetic optimization algorithm (AOA) is a math optimizer proposed to solve optimization challenges. Its capability to find the global solution comes from the behavior of four arithmetic operators: multiplication, division, subtraction and addition. Local minima stagnation and sluggish convergence are the major concerns of AOA. To handle these issues, three effective modifications are proposed. Information exchange is introduced among the search agents first. Then, promising solutions around the best and current solutions are visited by a plausible way based on the Gaussian distribution. Finally, quasi-opposition of the best solution is obtained to have a higher chance of approaching the global solution. The proposed approach is named as Information-Exchanged Gaussian AOA with Quasi-Opposition learning (IEGQO-AOA). 23 standard benchmark functions, 10 CEC2020 test functions and 1 real-life engineering design problem are solved by the proposed IEGQO-AOA and its competing peers such as the original and modified versions of AOA, dwarf mongoose optimization, reptile search algorithm, aquila optimizer, bat algorithm, sine cosine algorithm, original and enhanced version of salp swarm algorithm, dragonfly search algorithm, LSHADE-EpSin, stochastic fractal search, improved jaya and moth-flame optimization, perturbed stochastic fractal search and nelder-mead simplex orthogonal learning moth-flame optimization algorithm. Comparative results based on the statistical tests ratify the potential of IEGQO-AOA in solving problems concerning accuracy and convergence without compromising on the algorithm’s simplicity much.

Boosting Whale Optimizer with Quasi-Oppositional Learning and Gaussian Barebone for Feature Selection and COVID-19 Image Segmentation.

The online version contains supplementary material available at 10.1007/s42235-022-00297-8.

QQLMPA: A quasi-opposition learning and Q-learning based marine predators algorithm

Many engineering and scientific problems in the real-world boil down to optimization problems, which are difficult to solve by using traditional methods. Meta-heuristics are appealing algorithms for solving optimization problems while keeping computational costs reasonable. The marine predators algorithm (MPA) is a modern optimization meta-heuristic, inspired by widespread Lévy and Brownian foraging strategies in ocean predators as well as optimal encounter rate strategies in biological interactions between predator and prey. However, MPA is not without its shortcomings. In this paper, a quasi-opposition based learning and Q-learning based marine predators algorithm (QQLMPA) is proposed. This offers multiple improvements over standard MPA. Primely, Q-learning allows MPA to fully use the information generated by previous iterations. And also, quasi-opposition based learning serves to increase population diversity, reducing the risk of convergence to inferior local optima. Numerical experiments demonstrate better performance by QQLMPA on 32 benchmark optimization functions and three engineering problems: designs of pressure vessel, hydro-static thrust bearing, and speed reducer.

Reinforcement learning-based modified cuckoo search algorithm for economic dispatch problems

One of the crucial tasks of social development is carbon neutrality, which is mainly due to the emission of greenhouse gases. However, thermal power, which produces plenty of harmful gases, is still the main component of electric energy. Therefore, Economic Dispatch (ED) is proposed to utilize energy resources more efficiently and reduce the cost of power generation. ED is a nonlinear and nonconvex-constrained optimization problem that is difficult to optimize. In this paper, we propose a Reinforcement Learning-based Modified Cuckoo Search algorithm (RLMCS) to solve ED problems. The proposed algorithm employs the concept of Reinforcement Learning (RL) and develops an RL-based method to process population obtained from the explorative phase. The RL-based method can dynamically enhance the population based on cumulative rewards and the current environmental state. Thus, the comprehensive search ability of RLMCS has been well improved. Moreover, some proven technologies, i.e., Gaussian random walk, quasi-opposition learning, and adaptive switch parameter, are introduced to further enhance the efficiency of RLMCS. The performance of the RLMCS is tested on standard ED problems (6 and 11 units) and ED problems with valve-point effects (10, 14, and 40 units). RLMCS is also compared with some well-established CS variants. The experimental results have demonstrated that RLMCS is more competitive and robust.