Latest advances in use of bio-inspired jellyfish search algorithm for fixing optimization issues

This part focuses on using jellyfish search optimizer (JSO) in engineering optimization, prediction and classification, and the algorithmic fine-tuning of synthetic intelligence.

Engineering optimization

The jellyfish search optimizer (JSO) has been utilized in numerous engineering fields, reminiscent of energy methods and power technology, communication and networking, and civil and building engineering as detailed under.

Energy system and power technology

This part examines the makes use of of JSO in energy methods and energy-related fields. Rai and Verma⁶³ used JSO to seek out the financial load dispatch of producing items, contemplating transmission losses. The effectiveness of the proposed technique was evaluated by testing it on six methods beneath numerous masses. It was in contrast with the lambda-iterative and PSO algorithms to seek out probably the most environment friendly amongst them. JSO yielded the bottom gasoline value and transmission losses of the in contrast strategies.

Tiwari et al.⁶⁴ used JSO to research the impact of the set up of distributed technology (DG) and a capacitor financial institution (CB) on a radial distribution system (RDS). They carried out a cost-based evaluation that thought-about the main bills which are incurred as a result of set up, operation, and upkeep of DG and CB items. They examined JSO on the IEEE 33-bus RDS. The outcomes of their simulation have been in contrast with these of simulations of different strategies within the literature. JSO outperformed these different strategies by way of each energy loss minimization and revenue maximization.

Farhat et al.⁶⁵ used JSO to suggest an influence stream mannequin that included three varieties of power sources, which have been thermal energy turbines representing standard power sources, wind energy turbines (WPGs), and photo voltaic photovoltaic turbines (SPGs). They used a modified IEEE 30-bus check system to find out its feasibility. To look at the effectiveness of the proposed energy stream mannequin, the outcomes of its simulation have been in contrast with the outcomes of simulations of 4 different nature-inspired world optimization algorithms. The outcomes established the effectiveness of JSO in fixing the optimum energy stream (OPF) drawback with respect to each minimization of whole technology value and answer convergence.

Shaheen et al.⁶⁶ launched an environment friendly and strong approach that used JSO for optimum Volt/VAr coordination primarily based on a joint distribution system reconfiguration (DSR)with the mixing of distributed technology items (DGs) and the operation of distribution static VAr compensators (SVCs). JSO yielded the perfect answer and a comparability of the proposed JSO with comparable approaches demonstrated its usefulness in trendy management facilities.

Alam et al.⁶⁷ used JSO to trace the worldwide most energy level (GMPP) of the photo voltaic photovoltaic (PV) module beneath partial shading circumstances. Their outcomes advised that the JSO technique has good monitoring pace and accuracy. Additionally they discovered that the JSO technique tracks the GMPP in half of the time that’s taken by the PSO algorithm beneath each uniform and shaded circumstances.

Boutasseta et al.⁶⁸ used the JSO approach to switch the voltage of a photovoltaic array utilizing a lift direct present to direct present (DC–DC) converter. Their experimental outcomes revealed that JSO performs properly beneath each regular and disturbed working circumstances.

Abdulnasser et al.⁶⁹ used JSO for the optimum sizing and placement of DGs and capacitor banks (CBs). To elucidate the effectivity of the proposed algorithm, they thought-about numerous circumstances; the allocation of CBs solely, the allocation of DGs solely, and the allocation of each CBs and DGs. The outcomes thus obtained reveal that the JSO delivered the perfect outcomes with respect to technical, financial, and emission targets.

Ngo⁷⁰ used JSO to unravel the financial dispatch drawback and to cut back prices and gasoline consumption in energy methods. To confirm the feasibility and the effectiveness of the proposed scheme, they carried out two case research to check the optimization efficiency of the proposed technique from a number of financial views. The validation outcomes reveal that the proposed scheme offered extra pace, convergence, and robustness than the strategies to which it was in contrast.

Nusair et al.⁷¹ used JSO and different just lately developed algorithms (slime mould algorithm (SMA), synthetic ecosystem-based optimization (AEO), and marine predators algorithm (MPA)) to unravel each multi- and single-OPF goal issues for an influence community that incorporate versatile alternating present transmission system (FACTS) and stochastic renewable power sources. They in contrast these algorithms to generally obtainable alternate options within the literature reminiscent of PSO, moth flame optimization (MFO), and gray wolf optimization (GWO), utilizing an IEEE 30-bus check system. Their outcomes reveal that JSO and different just lately offered algorithms (MPA, SMA, and AEO) are more practical than PSO, GWO, and MFO in fixing OPF issues.

Eid⁷² used JSO to allocate distributed turbines (DG) and shunt capacitor (SC) banks optimally in distribution methods. He discovered JSO to be sensible and efficient in fixing such nonlinear optimization issues, yielding higher outcomes than different algorithms within the literature. Huang and Lin⁷³ used an improved jellyfish search optimizer (IJSO) to trace the utmost energy level (MPPT) beneath partial shade circumstances. Their outcomes confirmed that IJSO can precisely monitor the worldwide most energy level, and that it converged extra shortly than an improved particle swarm optimization (IPSO) algorithm.

Shaheen et al.⁵⁷ built-in a novel amalgamated heap-based agent with jellyfish optimizer (AHJFO) to optimize mixed warmth and energy financial dispatch (CHPED). They improved the effectivity of two newly developed strategies: the heap-based optimizer (HBO) and JSO. AHJFO incorporates an adjustment technique perform (ASF) to enhance exploration in a couple of iterations by enhancing the options which are generated utilizing HBO. Because the iterations proceed, exploitation is improved by updating options which are generated utilizing JSO. AHJFO is more practical than HBO and JSO in fixing the CHPED drawback for medium-sized 24-unit and enormous 96-unit methods. Simulation outcomes reveal the prevalence of the proposed AHJFO over HBO, JSO and different algorithms for fixing the CHPED issues.

Ginidi et al.⁵⁸ proposed an modern hybrid heap-based JSO (HBJSO) to enhance upon the efficiency of two just lately developed algorithms: the heap-based optimizer (HBO) and JSO. HBJSO makes use of the explorative options of HBO and the exploitative options of JSO to beat a number of the weaknesses of those algorithms of their commonplace varieties. HBJSO, HBO, and JSO have been validated and statistically in contrast by utilizing them to unravel a real-world optimization drawback of mixed warmth and energy (CHP) financial dispatch. HBJSO, HBO, and JSO have been utilized to 2 medium-sized 24-unit and 48-unit methods, and two massive 84 unit and 96-unit methods. The experimental outcomes display that the proposed hybrid HBJSO outperforms the usual HBO, JSO and different reported strategies when, utilized to CHP financial dispatch.

Shaheen et al.⁷⁴ proposed an enhanced quasi-reflection jellyfish optimization (QRJFO) algorithm for fixing the optimum energy stream drawback. Gasoline prices, transmission losses and pollutant emissions have been thought-about as multi-objective features. The efficiency of the proposed QRJFO algorithm was evaluated on the IEEE 57-bus, the sensible West Delta Area system and a big IEEE 118-bus. Simulation outcomes display the standard of the options and resilience of QRJFO.

Boriratrit et al.⁷⁵ used jellyfish search excessive studying machine (JS-ELM), the Harris hawk excessive studying machine (HH-ELM), and the flower pollination excessive studying machine (FP-ELM) to extend accuracy and scale back overfitting in electrical power demand forecasting. Their outcomes present that the JS-ELM offered a greater minimal root imply sq. error than the state-of-the-art forecasting fashions.

Ali et al.⁷⁶ offered an efficient optimum sizing approach for a hybrid micro-grid utilizing JSO. Their proposed sizing method considers uncertainty related to hybrid renewable sources. They investigated a number of working situations to judge the effectiveness of the proposed method and in contrast it to numerous optimization strategies. Their outcomes display the applicability of JSO to their drawback of curiosity.

Rai and Verma⁷⁷ used JSO to unravel a mixed financial emission drawback for an remoted micro-grid. They carried out exams on this micro-grid system, comprising conventional turbines and renewable power sources in two situations. They in contrast the outcomes with these obtained utilizing obtainable algorithms to show that the JSO algorithm was more practical than the others.

Yuan et al.⁷⁸ used the improved jellyfish search optimizer and help vector regression (IJSO-SVR) to unravel the issues of grid connection and energy dispatching which are attributable to non stationary wind energy output. IJSO displays good convergence means, search stability, and optimum-seeking means, and it’s more practical than standard strategies in fixing optimization issues. The IJSO-SVR mannequin outperformed different fashions within the literature and presents a extra economical and efficient technique of optimizing wind energy technology to unravel issues with its uncertainty and can be utilized in grid energy technology planning and energy system financial dispatch.

Chou et al.⁷⁹ used JSO and convolutional neural networks (CNNs) to judge the ability technology capability of plant microbial gasoline cells (PMFCs) on constructing rooftops. Their outcomes display the superior efficiency of JSO-optimized deep CNNs in studying picture options and their consequent suitability for establishing fashions for estimating energy technology by PMFCs.

Communication and networking

This part investigates using JSO within the discipline of communication and networking. Selvakumar and Manivannan⁸⁰ used JSO to beat the shortcomings of defragmentation in networking, and to enhance the standard of community providers. The proposed mixture of proactive/reactive defragmentation method and JSO (PR-DF-JSO) outperformed state-of-the-art spectrum defragmentation algorithms by way of spectrum utilization, community effectivity, and high quality of service supplied primarily based on the outcomes of experiments and commonplace high quality metrics. Particularly, decrease spectrum fragmentation complexity, a greater bandwidth fragmentation ratio, and fewer total connection blocking have been achieved.

Durmus et al.⁸¹ used swarm-based metaheuristic algorithms JSO, PSO, synthetic bee colony (ABC), and the mayfly algorithm (MA), to find out the optimum design of linear antenna arrays. They carried out in depth experiments on the design of 10-, 16-, 24- and 32-element linear arrays and decided the amplitude and the positions of the antennas. They carried out every of their experiments 30 occasions owing to the randomness of swarm-based optimizers, and their statistical outcomes revealed that the novel algorithms JSO and MA outperformed the well-known PSO and ABC strategies.

Aravind and Maddikunta⁸² proposed a novel optimum route choice mannequin to be used with the web of issues (IoT) within the discipline of healthcare that was primarily based on an optimized adaptive neuro-fuzzy inference system (ANFIS). They chose optimum routes for medical knowledge utilizing a brand new self-adaptive jellyfish search optimizer (SA-JSO) that was an enhanced model of the unique JSO algorithm³⁹. Their mannequin outperformed others.

Civil and building engineering

Structural optimization has turn into some of the vital and difficult branches of structural engineering, and it has consequently acquired appreciable consideration in the previous couple of many years⁸³. Chou and Truong³⁹ developed JSO, motivated by the conduct of jellyfish within the ocean to be used in civil and building engineering. They used JSO to unravel structural optimization issues, together with 25, 52, and 582-bar tower designs. Their outcomes confirmed that JSO not solely carried out finest but additionally required the fewest evaluations of goal features. Due to this fact, JSO is probably a superb metaheuristic algorithm for fixing structural optimization issues.

Chou and Truong⁴⁶ expanded the framework of the single-objective jellyfish search (SOJS) algorithm to a multi-objective jellyfish search optimizer (MOJS) for fixing engineering issues with a number of targets. MOJS integrates Lévy flight, an elite inhabitants, a fixed-size archive, a chaotic map, and the opposition-based leaping technique to acquire Pareto-optimal options. Three constrained structural issues (25, 160, and 942-bar tower designs) of minimizing structural weight and most nodal deflection have been solved utilizing the MOJS algorithm. MOJS is an efficient and environment friendly algorithm for fixing multi-objective optimization issues in civil and building engineering.

Kaveh et al.⁵² proposed a quantum-based JSO, named Quantum JSO (QJSO), for fixing structural optimization issues. QJSO is used to unravel frequency-constrained massive cyclic symmetric dome optimization issues. The outcomes thus obtained reveal that QJSO outperforms the unique JSO and has superior or comparable efficiency to that of different state-of-the-art optimization algorithms.

Rajpurohit and Sharma⁵⁶ proposed an enhancement of JSO by the implementation of chaotic maps in inhabitants initialization. They utilized their enhanced JSO to 3 classical constrained engineering design issues. Evaluation of the outcomes means that the sinusoidal map outperforms different chaotic maps in JSO and helps to seek out effectively the minimal weight design of a transmission tower.

Ezzeldin et al.⁸⁴ used JSO to develop optimum methods for the sustainable administration of saltwater intrusion into coastal aquifers primarily based on the finite ingredient technique (FEM). They examined the effectiveness of JSO by making use of it to an actual aquifer system in Miami Seashore to maximise its whole financial profit and whole pumping charge. JSO has additionally been utilized in a case research of the El-Arish Rafah aquifer, Egypt, to maximise the entire pumping charge. The leads to each circumstances have been in comparison with related leads to the literature, revealing that the JSO is an efficient and environment friendly administration software.

Chou et al.⁸⁵ used JSO and convolutional neural networks (CNNs) to foretell the compressive energy of ready-mixed concrete. Their analytical outcomes reveal that laptop vision-based CNNs outperform numerical data-based deep neural networks (DNNs). Thus, the bio-inspired optimization of laptop vision-based convolutional neural networks has promise for predicting the compressive energy of ready-mixed concrete.

Chou et al.⁸⁶ offered jellyfish search optimizer (JSO)-XGBoost and symbiotic organisms search (SOS)-XGBoost for forecasting the nominal shear capability of bolstered concrete partitions in buildings. Their proposed strategies outperform the ACI provision equation and grid search optimization (GSO)-XGBoost within the literature. Thus, they can be utilized to enhance constructing security, simplify a cumbersome shear capability calculation course of, and scale back materials prices. Their systematic method additionally supplies a basic framework for quantifying the efficiency of assorted mechanical fashions and empirical formulation which are utilized in design requirements.

Truong and Chou⁴⁷ proposed a novel fuzzy adaptive jellyfish search optimizer (FAJSO) to be used within the stacking system (SS) of machine studying. They built-in the JSO, the fuzzy adaptive (FA) logic controller, and stacking ensemble machine studying. Its software to building productiveness, the compressive energy of a masonry construction, the shear capability of bolstered deep beams, the axial energy of metal tube confined concrete, and the resilient modulus of subgrade soils was investigated. Their outcomes point out that the FAJSO-SS outperformed different strategies. Accordingly, their proposed fuzzy adaptive metaheuristic optimized stacking system is efficient for offering engineering informatics within the planning and design part.

Prediction and classification

Prediction and classification are required in a wide range of areas that contain time sequence and cross-sectional knowledge^{87, 88}. This part considerations articles by which JSO has been used alone or built-in with machine/deep studying algorithms for prediction and classification.

Almodfer et al.⁸⁹ employed a random vector purposeful hyperlink (RVFL) community that was optimized by JSO, AEO, MRFO, and SCA to foretell the efficiency of a photo voltaic thermo-electric air-conditioning system (STEACS). Their outcomes revealed that the RVFL-JSO outperformed the opposite algorithms in predicting all responses of the STEACS with a correlation coefficient of 0.948–0.999. They really helpful its use for modeling STEACS methods.

Chou et al.⁹⁰ used JSO to optimize the convolutional neural community (CNN) hyper-parameters to make sure the accuracy and stability of CNN in predicting energy consumption. Their analytical outcomes present insights into the formulation of power coverage for administration items and may help energy provide companies to distribute regional energy in a manner that minimizes pointless power loss.

Barshandeh et al.⁹¹ utilized JSO and the marine predator algorithm (MPA) to develop a learning-automata (LA)-based hybrid algorithm for benchmark perform optimization and fixing knowledge clustering drawback. They utilized the proposed algorithm to 10 datasets and in contrast it with competing algorithms utilizing numerous metrics; the hybrid algorithm outperformed. Desuky et al.⁹² used JSO to categorise imbalanced and balanced datasets. They carried out experiments on 18 actual imbalanced datasets, and the proposed technique carried out comparably with well-known and just lately developed strategies.

Chou and Truong⁸⁸ examined JSO and different parameter-less algorithms (TLBO, SOS) by utilizing them within the hyperparameters finetuning of least squares help vector regression (LSSVR) to develop a novel forecasting system. The linear time-series has been optimized utilizing nonlinear machine studying fashions to determine historic patterns of regional power consumption. Analytical outcomes verify that the proposed system, JSO-LSSVR, can predict multi-step-ahead power consumption time sequence extra precisely than can the linear mannequin.

Chou et al.⁹³ developed a weighted-feature least squares help vector regression (WFLSSVR) mannequin that’s optimized by JSO to foretell the height friction angle (shear energy) of fiber-reinforced soil (FRS), which is a well-liked materials to be used in constructing geotechnical buildings. Their outcomes confirmed that JSO-WFLSSVR outperformed baseline, ensemble, and hybrid machine studying fashions, in addition to empirical strategies within the literature. The JSO-WFLSSVR mannequin can also be efficient for choosing options and may help geotechnical engineers to estimate the shear energy of FRS.

Hoang et al.⁹⁴ carried out a help vector machine classifier that was optimized utilizing JSO for the automated classification of the severity of concrete spalling. It partitions enter knowledge into two courses, shallow spalling and deep spalling. Experimental outcomes, supported by the Wilcoxon signed-rank check, reveal that the newly developed technique is very efficient for classifying the severity of concrete spalling with an accuracy charge of 93.33%, an F1 rating of 0.93, and an space beneath the receiver working attribute curve of 0.97.

Siddiqui et al.⁹⁵ used JSO to calculate the optimum switching angle within the modulation vary to eradicate desired lower-order harmonics in a multilevel inverter (MLI) voltage management software. The entire harmonic distortion (THD) values of five-, seven-, and nine-level have been computed utilizing JSO and in contrast with these obtained utilizing the highly effective differential evolution (DE) algorithm. The outcomes thus obtained clearly demonstrated that the output of an MLI in JSO displays THD that’s superior to that within the output of DE for low and medium values of the modulation index.

Çetinkaya and Duran⁹⁶ used JSO and different just lately developed optimization algorithms [marine predators’ algorithm (MPA), tunicate swarm algorithm (TSA), mayfly optimization algorithm (MOA), chimp optimization algorithm (COA), slime mould optimization algorithm (SMOA), archimedes optimization algorithm (AOA), and equilibrium optimizer algorithm (EOA)] to enhance the precision of the clustering-based segmentation of vessels. Simulation outcomes of those algorithms exhibited comparable convergence charges and error performances. Statistical analyses demonstrated that the steadiness and robustness of every metaheuristic method sufficed to separate vessel pixels from the background pixels of a retinal picture.

Wang and Gao⁹⁷ used the multi-objective jellyfish search optimizer (MOJS) to find out the weights of kernel features. Based on their experimental outcome regarding three American photo voltaic websites, the proposed system that integrates with MOJS offered the next interval protection charge and a narrower interval width than these of different methods.

Zhao⁹⁸ used single-objective JSO to categorise mind perform in human mind perform parcellation. Experimental outcomes present that that the brand new technique not solely has a higher looking means than different partitioning strategies, but additionally can get hold of higher spatial buildings and stronger purposeful consistency.

Lei et al.⁶¹ proposed an enhanced algorithm, generally known as the fractional-order modified technique and Gaussian mutation mechanism jellyfish search optimizer (FOGJSO), to foretell rural resident revenue. They used FOGJSO to optimize the order of a discrete fractional time-delayed gray mannequin for forecasting rural resident revenue. The outcomes reveal that FOGJSO carried out significantly better with respect to precision and convergence pace than did different strategies.

Shubham et al.⁹⁹ used JSO for clustering between a dish kind stirling photo voltaic generator, a micro hydro turbine, a diesel generator, a flywheel power storage system, a brilliant magnetic power storage system and an electrical car in a renewable power primarily based microgrid to stabilize the frequency and tie line energy within the system. They in contrast the efficiency of the JSO primarily based twin stage controller with these of the black widow optimization algorithm, GA and the PSO-based controller, with respect to overshoot, undershoot, settling time and determine of demerit. JSO outperformed different optimization algorithms when used to tune twin stage (1+PI)TID controller involving a microgrid-based electrical car.

Finetuning of synthetic intelligence

Hyper-parameter optimization is crucial to the event of environment friendly fashions in machine studying and deep studying algorithms, in addition to for high quality management in industrial manufacturing^{100, 101}. JSO is an environment friendly and modern algorithm that’s utilized in hyper-parameter optimization.

Chou et al.¹⁰² used JSO to optimize the hyper-parameters of a deep studying mannequin that is known as residual community (ResNet) and is used to categorise the deflection of bolstered concrete beams, primarily based on observations made by laptop imaginative and prescient. Their work helps an modern technique that engineers can use to measure the deflection of bolstered concrete beams. The outcomes of their evaluation revealed that the proposed ResNet mannequin that was optimized by JSO was extra correct than standard ResNet.

Dhevanandhini and Yamuna¹⁰³ used JSO to seek out the optimum coefficients of a discrete wavelet remodel (DWT) to enhance environment friendly multiple-video watermarking. They analyzed the efficiency of the proposed technique utilizing numerous metrics and in contrast it with the DWT-based watermarking method, which it outperformed.

Elkabbash et al.¹⁰⁴ proposed a novel detection system that was primarily based on optimizing the random vector purposeful hyperlink (RVFL) utilizing JSO, following the dimensional discount of Android software options. They used JSO to find out the optimum configurations of RVFL to enhance classification efficiency. The optimized RVFL minimized the runtime of the fashions with the perfect efficiency metrics.

Gouda et al.¹⁰⁵ employed JSO to unravel the issue of evaluating the parameters of the polymer trade membrane gasoline cells (PEMFCs) mannequin. The utmost proportion voltage-biased error was ± 1% in all check circumstances, indicating that JSO can resolve this drawback extra successfully than different algorithms.

Youssef et al.¹⁰⁶ used JSO to estimate the parameters of a single-phase energy transformer from the present and voltage beneath any load. They think about distinction between the estimated and precise values as the principle goal perform that have to be minimized. Experimental outcomes revealed that the parameters of the transformer equal circuit have been precisely obtained, indicating that the algorithm can be utilized to estimate the parameters of a single-phase transformer.

Kızıloluk and Sert¹⁰⁷ adopted JSO to optimize the hyper-parameters of the Alex Internet CNN mannequin for function extraction within the Sooner R-CNN-JSO mannequin for the early detection of hurricanes from satellite tv for pc photos. The aim was to alert folks about upcoming disasters and thus reduce casualties and materials losses. Their outcomes demonstrated that hyper-parameter optimization elevated the detection efficiency of the proposed method by 10% over that of Alex Internet with out optimized hyper-parameters. The common precision of Hurricane-faster R-CNN-JS was 97.39%, which was remarkably greater than these of different approaches.

Bisht and Sikander¹⁰⁸ used JSO to optimize the parameters of the photo voltaic photovoltaic (PV) mannequin. They used JSO to optimize the parameters of a single-diode PV mannequin utilizing numerous efficiency measures, reminiscent of PV traits, power-voltage, and current-voltage curves, relative error (RE), root imply sq. error (RMSE), imply absolute error (MAE), and normalized imply absolute error (NMAE). Their proposed approach offered higher outcomes than different strategies, with a decrease RE, RMSE, MAE, and NMAE; it additionally converged quickly.

Azam et al.¹⁰⁹ utilized JSO to dampen out low-frequency oscillations (LFOs) by tuning the essential parameters of standard lead-lag kind energy system stabilizers. JSO is used to tune time-domain simulations of the angular frequency, rotor angle, and management sign. They examined this technique on two separate multimachine networks that have been uncovered to a three-phase fault, and in contrast it with two well-known optimization algorithms, known as PSO and the backtracking search algorithm (BSA). Their outcomes present that JSO offered higher damping energy system ratio than did the opposite algorithms. Furthermore, the JSO-based method converged in fewer iterations.

Raja and Periasamy¹¹⁰ offered the block chain and JSO-based deep generative adversarial neural community (DGANN) technique for the distributed routing scheme of a wi-fi sensor community (WSN). They used the block chain routing protocol to detect and retailer packets and to switch them from the supply to the vacation spot effectively to enhance the safety and effectivity of the DGANN technique. They used JSO to optimize the load parameters of the DGANN technique. The simulation outcomes display that within the routing of a WSN, DGANN with optimized parameters outperforms others strategies, such because the multidimensional scaling-map, the trust-aware routing protocol by means of a number of attributes, and dynamic rate-aware categorized key distributional safe routing algorithms.

Usharani et al.¹¹¹ used JSO to optimize the hyperparameters of lengthy short-term reminiscence (LSTM) networks to boost the error metrics of the approximate multiplier. They used their proposed pre-trained LSTM mannequin to generate approximate design libraries for the totally different truncation ranges as a perform of space, delay, energy and error metrics. Their experimental outcomes on an 8-bit multiplier with a picture processing software reveals that the proposed approximate computing multiplier achieved a superior space and energy discount with excellent error charges.

Nyong-Bassey and Epemu¹¹² used JSO and PSO to determine servomechanism parameters utilizing a two-step method, involving a first-order switch perform and iterative minimization of a health rating that’s derived from the basis imply squared error between the experimental and simulated place responses of the servomechanism of an equal state-space mannequin construction. The simulated angular place step responses of the servomechanism that runs the JSO and PSO algorithms confirmed very intently with one another, by way of root imply squared error. Desk 2 summarizes latest advances within the software of the jellyfish search optimizer.