Search Optimization Algorithm Research Articles

A novel Adaptive Jellyfish Search algorithm (AJFS) for maximum power optimization of photovoltaic systems: performance evaluation and analysis

ABSTRACT In solar photovoltaic (SPV) systems, optimizing output under various meteorological conditions relies on the Maximum Power Point (MPP) tracking controller. However, the presence of multiple peaks due to partial shading complicates this tracking process. While traditional and soft computing methods are commonly employed for MPP tracking, they face limitations such as the fixed step size in conventional methods and a lack of randomness in soft computing approaches once they reach a certain MPP. To address these challenges, a unique optimization technique known as the Adaptive Jellyfish Search (AJFS) method has been proposed. This method conducts both global and local searches simultaneously in a single step, enhancing the effectiveness of MPP tracking. To evaluate its performance and resilience, zero, weak, moderate, and strong shading patterns are employed in simulations, with comparisons made against traditional Jellyfish Search (JFS) and Particle Swarm Optimization (PSO) techniques. The newly suggested AJFS approach demonstrates significant improvements over traditional methods. It reduces convergence time by 49% and offers additional motivating features, including zero risk of failure, minimized oscillation in power parameters, and enhanced energy production by 1.5%. Moreover, it enables smooth tracking of the MPP, particularly in dynamically changing shading patterns. Overall, the AJFS method presents a promising solution for efficient MPP tracking in SPV systems, overcoming limitations of conventional approaches and demonstrating superior performance under various shading conditions. Its ability to simultaneously conduct global and local searches in a single step makes it well suited for optimizing energy production in real-world scenarios.

Elman neural network optimized by improved golden search optimization algorithm for optimal designing of the hybrid renewable energy systems

ABSTRACT Hybrid renewable energy systems (HRESs) could offer a promising solution to the challenges of providing a dependable, economical and sustainable energy’s source. The integration of these technologies can help to overcome the limitations of intermittency, variability, and storage. Further, the economic and environmental benefits of HRESs make them an attractive option for widespread adoption in the future. However, designing an optimal configuration that can guarantee stable production at the minimum LCOE (Levelized Cost of Electricity) and LPSP (Loss of Power Supply Probability) values is the main concern of researchers. In this regard, the present study aims to optimize the configuration of a hybrid plant and determine the plant’s economic viability. The proposed plant, containing of a storing unit (VRFB, Vanadium Redox Flow Batteries-based battery energy storing), a solar photovoltaic (PV) plant, a wind farm, and a hydrogen storage system (for running an FC (Fuel Cell)), is designed to provide a stable production to the grid at a minimum LCOE value under least LPSP value and extra energy output. The development of the proposed optimal model for the HRES is based on an Elman Neural Network (ENN) model established by a new optimization algorithm (i.e. Improved Golden Search Optimization Algorithm (IGSOA)). The model is applied to a case study, San Luis Ayucan in Mexico, to verify the method efficacy. From the results, the storing system, including in cooperation battery and hydrogen indicate the main cost driver for each model arrangement with total cost percentage of 63.4%, 70.2%, 73.2%, and 73.7% for the proposed ENN/IGSOA, ENN, SVR, and ANN, respectively. Further, an ANN model had zero’s both an excess energy and an LPSP value; so, the system needs to rely heavily on energy storing to ensure that the stable load can be fulfilled. As a result, this increases the system’s total rate and subsequently results in a higher LCOE.

Advanced Harmonic Mitigation in Photovoltaic Grid-Connected Systems: Jellyfish Search Optimization Approach

Increasing prevalence of nonlinear loads (NLL) in modern power systems poses significant challenges, particularly in terms of harmonic distortion. This distortion degrades the performance and efficiency of photovoltaic (PV) grid-connected systems (PV-GCS), demanding advanced control strategies. This study presents a unique optimization-based method that employs the Jellyfish Search Optimization (JSO) algorithm to enhance the Shunt Active Power Filter (SAPF) for effective harmonic reduction in PV-GCS with a high penetration of NLL in the distribution network. The study aims to reduce total harmonic distortion (THD) and regulate the DC-bus voltage (Vdc) in SAPF. A comprehensive comparison examination is performed between JSO and three frequently utilized optimization algorithms: genetic algorithm (GA), particle swarm optimization (PSO), and golden eagle algorithm (GE), to investigate the efficiency of JSO algorithm. The reduced THD by the JSO is only 1.32 percent, smoothly regulated the Vdc with a short settling time, without overshooting. These findings indicate that JSO outperforms others, emphasizing that it has the potential to improve power quality (PQ) in PV-GCS with NLL. This study presents a strong foundation for minimizing harmonics in PV integrating to the grids, which contributes to improved system reliability and efficiency.

Efficient parameter extraction in PV solar modules with the diligent crow search algorithm

In this study, we introduce a novel method that can be seamlessly integrated into existing metacognitive algorithms, significantly enhancing their performance during both exploitation and exploration phases. This method offers several advantages, including ease of implementation and simplicity in calculations, which collectively accelerate convergence to the global minimum and enhance the algorithm's robustness. Notably, it effectively avoids local minima, ensuring the algorithm does not become trapped. Furthermore, this method eliminates the need for developing new metacognitive algorithms. To demonstrate its benefits, we apply this method to the crow search optimization algorithm (CSA), which is notably deficient in convergence speed, robustness, stability, and escaping local minima. Consequently, the enhanced algorithm is termed the diligent crow search optimization algorithm (DCSA). Additionally, we utilize the powerful DCSA algorithm to identify the parameters of solar cells, aiming to maximize power output from solar energy—a critical global concern. To evaluate the proposed algorithm, we tested it on various solar cell models, including one-diode, two-diode, and three-diode configurations, as well as several widely used solar panels such as SM55, KC200GT, and SW255. We also examined the impacts of radiation, temperature, and unknown parameters on these solar panels. The simulation results demonstrate that implementing the proposed method on the crow algorithm resulted in a 98% improvement in stability and a sevenfold increase in convergence speed.

Modeling the emitted carbon dioxide and monoxide gases in the gasification process using optimized hybrid machine learning models

Abstract The machine learning methods are hereby proposed to predict the amount of Carbon Monoxide (CO) and Carbon Dioxide (CO₂) emissions in a gasification process, which is one of the most important enabling technologies for carbon-containing materials, such as coal, biomass, and waste toward producing end products of worth, such as syngas, hydrogen, and synthetic fuels. In an attempt to support efforts for improving the emission prediction-a key criterion for enhancing efficiency and further, the environmental performance of gasification-two new advanced algorithms are being applied for the optimization of the model of a random forest: the Jellyfish Search Optimizer (JSO) and Sooty Tern Optimization Algorithm (STOA). The tuned RFJS (RF+JSO) was the best of these configurations, providing the least RMSE of 0.593 on test data and the highest R 2 on validation of 0.983, proving to be most effective for the prediction of emissions. This goes to attest that the model RFJS would be a strong tool in real-time-based carbon emissions reduction due to its effectiveness in dealing with major implications from environmental monitoring to regulation and further into sustainable energy production.

Application of Sooty Tern Optimization Algorithm on Solar‐Wind‐Battery‐Thermal Integrated Dynamic Economic Emission Dispatch Problems

ABSTRACTThe current challenges faced by conventional power plants, including increasing load demand over time, high generation costs, and excessive emissions from fossil fuels, have been helped to overcome by the integration of renewable energy sources (RESs) alongside conventional thermal power units. In this article, traditional dynamic economic emission dispatch (DEED) is enhanced by incorporating RESs, including two solar units, two wind units, and one battery power unit, forming the solar‐wind‐battery‐thermal (SWBT) integrated DEED (SWBTDEED). This integration aimed at reducing generation costs and minimizing excessive fuel emissions, and combining cost and emissions over a 24 h period. Four different test systems, each incorporating 6, 10, 30, and 40 thermal units alongside the same RESs, are considered to meet varying load demands hourly throughout the day. This article demonstrates that, in addition to reducing generation costs, SWBTDEED is capable of reducing emissions by 38.28%, 28.48%, 20.67%, and 20.44% for four test systems, thereby protecting the environment. The sooty tern optimization algorithm (STOA) is proposed in this article for solving complex DEED and SWBTDEED problems, considering various constraints such as generation limits, ramp rate limits, valve point loading, and Weibull distribution. Finally, the robustness, optimization efficiency, and capability of the STOA technique in handling complex nonlinear constraints are demonstrated in the results section, showcasing its ability to achieve optimal results compared to other algorithms such as the sine‐cosine algorithm, backtracking search algorithm, differential evolution, and particle swarm optimization.

Process Optimization Using Cuckoo Search Algorithm for the Manufacturing of Resin Transfer Moulded Composite Parts

An in-house coded cuckoo search (CS) optimization algorithm integrated with a finite element simulation model was developed for resin transfer moulding (RTM) process optimization. At first, the mould filling and curing phases, the vital stages of the RTM process were modelled in the COMSOL multi-physics simulator for RTM6 resin – carbon fibre reinforced composite part. Then, the model was imported to the CS optimization algorithm scripted in MATLAB using the COMSOL live link for MATLAB. The CS algorithm was developed for the minimization of dry spot content by finding the optimal positions of gates and vents during the mould-filling stage and the minimization of the thermal gradient by finding the optimal mould temperature during the curing stage. From the optimization results, there was a decrease in dry spot content and thermal gradient with an increase in generations. With the generations, converged-stable-optimal solutions were obtained. A dry spot content of 3% for one gate and one vent and 0.56% for two gates and one vent was obtained for two-dimensional and three-dimensional composite plates, respectively. From the curing phase optimization results, a minimum thermal gradient of 0.86 K with 98.1% degree of cure was obtained for the optimal mould temperature of 433 K. The developed CS algorithm predicted the better-automated mould-fill and cure phase optimal solutions for the studied composite part.

Vehicle Travel Time Prediction Based on SSA-LSTM

Highway travel time, defined as the time difference between a vehicle entering and exiting the highway, is primarily influenced by factors such as the highway's characteristics, current road conditions, and the driver's behavior. Travel time is a crucial parameter for assessing the operational state of a highway and serves as an important reference for both drivers when selecting routes and for traffic managers in implementing control measures. Therefore, predicting highway travel time is of significant importance. Long Short-Term Memory (LSTM) is a type of recurrent neural network, an improved version of the traditional recurrent neural network, known for its excellent performance in predicting sequential data, such as time-series data on highway travel times. In operations research, search optimization algorithms have been a key area of focus in conjunction with machine learning. The Sparrow Search Algorithm (SSA), a relatively new search optimization algorithm, boasts high convergence speed and accuracy, along with strong global search capabilities, reducing the risk of getting trapped in local optima. This study utilizes vehicle entry and exit data collected by the ETC system at the Jin-Gang Expressway toll stations to analyze the highway's basic information. Building upon the traditional LSTM model, we integrate the SSA to optimize the LSTM model parameters. By using SSA to search for the optimal parameters, we form a new SSA-LSTM model. Finally, we apply this model to predict travel time data, showing a 120% improvement in prediction accuracy compared to the original LSTM model.

Flexible transmissive colors with enhanced purity and brightness through overlapping multi-cavity resonances.

We demonstrate flexible transmissive structural color filters with enhanced color purity and brightness by exploiting resonance overlap within multiple cavities in penta-layered structures. Using an inverse design method that combines optimization and exhaustive search algorithms, the material choices and layer thicknesses are determined through a loss function based on the CIE XYZ color space, optimizing both color purity and brightness. The resulting color gamut is comparable to standard RGB, as assessed in the CIE xy color space, with luminance (Y from CIE 1931 model) values for the fabricated transmissive RGB colors being 0.14, 0.51, and 0.14. The contribution of each cavity is thoroughly analyzed using optical admittance diagrams and resonant mode calculations. Furthermore, the transmissive colors on a flexible substrate exhibit excellent durability, retaining consistent transmission efficiency and color purity even after 4,000 bending cycles and performing reliably at a bending radius of 5 mm. The versatility of this design approach makes them suitable for a wide range of applications, including e-paper displays, image sensors, flexible wavelength-selective optoelectronic devices, and decorations.

Optimized Hybrid Deep Learning Framework for Early Detection of Alzheimer's Disease Using Adaptive Weight Selection.

Alzheimer's disease (AD) is a progressive neurological disorder that significantly affects middle-aged and elderly adults, leading to cognitive deterioration and hindering daily activities. Notwithstanding progress, conventional diagnostic techniques continue to be susceptible to inaccuracies and inefficiencies. Timely and precise diagnosis is essential for early intervention. We present an enhanced hybrid deep learning framework that amalgamates the EfficientNetV2B3 with Inception-ResNetV2 models. The models were integrated using an adaptive weight selection process informed by the Cuckoo Search optimization algorithm. The procedure commences with the pre-processing of neuroimaging data to guarantee quality and uniformity. Features are subsequently retrieved from the neuroimaging data by utilizing the EfficientNetV2B3 and Inception-ResNetV2 models. The Cuckoo Search algorithm allocates weights to various models dynamically, contingent upon their efficacy in particular diagnostic tasks. The framework achieves balanced usage of the distinct characteristics of both models through the iterative optimization of the weight configuration. This method improves classification accuracy, especially for early-stage Alzheimer's disease. A thorough assessment was conducted on extensive neuroimaging datasets to verify the framework's efficacy. The framework attained a Scott's Pi agreement score of 0.9907, indicating exceptional diagnostic accuracy and dependability, especially in identifying the early stages of Alzheimer's disease. The results show its superiority over current state-of-the-art techniques. The results indicate the substantial potential of the proposed framework as a reliable and scalable instrument for the identification of Alzheimer's disease. This method effectively mitigates the shortcomings of conventional diagnostic techniques and current deep learning algorithms by utilizing the complementing capabilities of EfficientNetV2B3 and Inception-ResNetV2 by using an optimized weight selection mechanism. The adaptive characteristics of the Cuckoo Search optimization facilitate its application across many diagnostic circumstances, hence extending its utility to a wider array of neuroimaging datasets. The capacity to accurately identify early-stage Alzheimer's disease is essential for facilitating prompt therapies, which are crucial for decelerating disease development and enhancing patient outcomes.

Osteoporosis Disease Detection using Optimized Elman Recurrent Neural Network based on Hybrid Bacterial Colony Optimization and Tabu Search Algorithm

Bone loss and fragility are indications of osteoporosis, a condition caused by calcium deficiency. The detection of osteoporosis is a significant and difficult diagnostic endeavor. Elman recurrent neural network (ERNN) is a well-known medical disease detection method due to its modeling sequential data and capturing temporal dependencies. ERNN training can be computationally costly and necessitates precise adjustment of hyperparameters. In this research, optimized ERNN is used to predict osteoporosis diseases to achieve high detection accuracy and to improve the global convergence rate. The new hybrid method is used to optimize the hyperparameters of ERNN based on the bacterial colony optimization (BCO) and tabu search (TS) algorithm, which is called IBCO-ERNN. The hybrid technique can efficiently explore the solution space by combining BCO's global exploration capabilities and TS's local exploitation capability, perhaps leading to better solutions to hyperparameter optimization problems. The hybrid BCO-TS strategy trains the ERNN model to prevent local optima and improve convergence rate. The experimental results demonstrated that the proposed IBCO-ERNN obtained high accuracy and fast convergence compared to other detection methods.

A multi-strategy enhanced reptile search algorithm for global optimization and engineering optimization design problems

The reptile search algorithm (RSA) is a well-known swarm-based metaheuristic algorithm inspired by the hunting behaviors of crocodiles. To overcome the problems of falling into local optima and premature convergence, this paper proposes a multi-strategy enhanced reptile search algorithm (MRSA), which integrates a novel dynamic evolutionary sense, prey approaching strategy and Cauchy mutation strategy. The prey approaching strategy comes from the secretary bird optimization algorithm and is applied to strengthen the exploration capability of RSA. A comparative performance analysis is conducted using the CEC2005, CEC2017 and CEC2022 benchmark functions. And fifteen algorithms are employed for the performance comparison. The results of numerical, convergence curves, boxplots, Wilcoxon rank-sum test and Friedman ranking confirm the efficacy and stability of proposed MRSA, indicating its superior performance compared to other algorithms. Moreover, seven practical engineering design tasks are used to test the performance of MRSA in real-world optimization problems. The results also show that MRSA can efficiently obtain better optimal solution compared to existing methods.

Enhanced the Maximum Power Point Tracking (MPPT) of Photovoltaic Systems Using the Flying Squirrel Search Optimization (FSSO) algorithm and Feed Forward Neural Network

In this current Investigation, a solar PV system is applied. The Flying Squirrel Search Optimization (FSSO) algorithm for Maximum Power Point Tracking (MPPT) is examined. The flying squirrel's movement serves as inspiration for the FSSO algorithm, which simulates their movements and evaluates fitness to find the optimal voltage and current levels for maximum power output. Through dynamic positioning of "squirrels" (potential solutions), the algorithm strives to find the optimal voltage and current combination, hence optimizing the PV system's total efficiency. The MATLAB script that is included demonstrates the unique optimization method of the FSSO algorithm for MPPT in a solar PV system. The parameters and movement rules of the script can be customized to match the unique features of the PV system, offering application versatility. In general, these methods raise. Before applying the FSSO algorithm, ANN was applied to aid in enhancing MPPT's performance by creating an input-output model. ANN results are based on 8761 datasets collected from (www.kaggle.com). ANN resulted in the best validation performance obtained at epoch 30, which is a total of 36 epochs. The coefficient of determination (R-squared) for the linear regression between the predictions of the neural network and the actual target values is displayed as a regression equal to 0.84666. The results concluded that the neural network has reasonably good predictive performance. Based on these results, applying FSSO using 100 iterations, the results concluded that the maximum power point of tracking was accurately determined based on photovoltaic resources.

A deep decentralized privacy-preservation framework for online social networks

This paper addresses the critical challenge of privacy in Online Social Networks (OSNs), where centralized designs compromise user privacy. We propose a novel privacy -preservation framework that integrates blockchain technology with deep learning to overcome these vulnerabilities. Our methodology employs a two-tier architecture: the first tier uses an elitism-enhanced Particle Swarm Optimization and Gravitational Search Algorithm (ePSOGSA) for optimizing feature selection, while the second tier employs an enhanced Non-symmetric Deep Autoencoder (e-NDAE) for anomaly detection. Additionally, a blockchain network secures users’ data via smart contracts, ensuring robust data protection. When tested on the NSL-KDD dataset, our framework achieves 98.79% accuracy, a 10% false alarm rate, and a 98.99% detection rate, surpassing existing methods. The integration of blockchain and deep learning not only enhances privacy protection in OSNs but also offers a scalable model for other applications requiring robust security measures.

Optimal properties of hysteretic dampers to minimize peak floor accelerations in multi-story buildings subjected to earthquakes

In this study, the optimal reduction of seismic peak floor accelerations in buildings equipped with hysteretic dampers is investigated. The structures are modeled as linear elastic shear buildings, and the seismic demand is modeled as a stochastic process. The optimal properties and height-wise distribution of the hysteretic dampers are found using a pattern search optimization algorithm. The objective function is defined in terms of the stochastic non-stationary response of the structure, which is obtained using the Explicit Time Domain Method in combination with statistical linearization. Possible influence of the fundamental period of the structure, the frequency content of the excitation, and the number of stories, on the optimal properties of the hysteretic dampers are analyzed. The effects of the optimal solutions on other response quantities, such as inter-story drifts, ductility demand on the hysteretic dampers, energy dissipation, and floor response spectra, are also assessed. Findings of this study are validated by a case study that considers a real building model subjected to actual ground motion acceleration records. The main findings are: a) optimally designed hysteretic dampers are indeed effective in reducing the seismic peak floor acceleration response; and b) optimal non-uniform height-wise distributions of hysteretic dampers are essentially equal to or at most somewhat better (but not by a wide margin) than optimal uniform height-wise distributions.

Optimal parameter identification of adaptive fuzzy logic MPPT based-bald eagle search optimization algorithm to boost the performance of PEM fuel cell

The output power of proton exchange membrane (PEM) fuel cell is dependent on operating temperature and the membrane water content. Changing the operation condition changes the location maximum power point (MPP) on the nonlinear curve of power versus the current. Therefore, a robust MPP tracking strategy is obligatory to grantee the work of PEM fuel cell around or close the MPP and boost the harvested energy. The suggested tracker is based on the bald eagle search (BES) optimization algorithm to identify the best values to entirely advantage the inherent flexibility of fuzzy logic control (FLC) system furthermore to accomplish rapid and precise tracking. Throughout the optimization procedure, the gains of membership functions of FLC are assigned to be decision variables, while the integral of error is the objective function. To approve the advantage of BES, a comparison with gradient-based optimizer (GBO), osprey optimization algorithm (OOA), particle swarm optimization (PSO), pelican optimization algorithm (POA), blue monkey algorithm (BMA) and henry gas solubility optimization (HGS) is performed. The BES has the highest performance compared with other optimizers; it achieves the best value of 1.7638 flowed by GBO (1.7667) whereas the worst value of 1.7987 is obtained by POA. Additionally, the lowest STD of 0.0046 is achieved by BES followed by GBO (0.0078) whereas the worst value of STD of 0.0243 is obtained by HGS. Finally, the optimized FLC-MPPT-based BES is compared with commonly MPPTs including classical FLC and perturb & observe in terms of dynamic and steady state conditions. The comparison demonstrated that the suggested FLC-MPPT-based BES has fast tracking speed and diminishes the oscillations around MPP in steady state.

An adaptation of hybrid binary optimization algorithms for medical image feature selection in neural network for classification of breast cancer

The performance of neural network is largely dependent on their capability to extract very discriminant features supporting the characterization of abnormalities in the medical image. Several benchmark architectures have been proposed and the use of transfer learning has further made these architectures return good performances. Study has shown that the use of optimization algorithms for selection of relevant features has improved classifiers. However continuous optimization algorithms have mostly been used though it allows variables to take value within a range of values. The advantage of binary optimization algorithms is that it allows variables to be assigned only two states, and this have been sparsely applied to medical image feature optimization. This study therefore proposes hybrid binary optimization algorithms to efficiently identify optimal features subset in medical image feature sets. The binary dwarf mongoose optimizer (BDMO) and the particle swarm optimizer (PSO) were hybridized with the binary Ebola optimization search algorithm (BEOSA) on new nested transfer functions. Medical images passed through convolutional neural networks (CNN) returns extracted features into a continuous space which are piped through these new hybrid binary optimizers. Features in continuous space a mapped into binary space for optimization, and then mapped back into the continuous space for classification. Experimentation was conducted on medical image samples using the Curated Breast Imaging Subset of Digital Database for Screening Mammography (DDSM+CBIS). Results obtained from the evaluation of the hybrid binary optimization methods showed that they yielded outstanding classification accuracy, fitness, and cost function values of 0.965, 0.021 and 0.943. To investigate the statistical significance of the hybrid binary methods, the analysis of variance (ANOVA) test was conducted based on the two-factor analysis on the classification accuracy, fitness, and cost metrics. Furthermore, results returned from application of the binary hybrid methods medical image analysis showed classification accuracy of 0.8286, precision of 0.97, recall of 0.83, and F1-score of 0.99, AUC of 0.8291. Findings from the study showed that contrary to the popular approach of using continuous metaheuristic algorithms for feature selection problem, the binary metaheuristic algorithms are well suitable for handling the challenge. Complete source code can be accessed from: https://github.com/NathanielOy/hybridBinaryAlgorithm4FeatureSelection

Collaborative planning of electric vehicle integrated charging and swapping stations and distribution network for carbon emission reduction

Electric vehicle (EV) integration into the distribution network (DN) is a significant measure for reducing carbon dioxide emissions, yet existing studies have not fully explored the carbon reduction potential of the EV. This article proposes an innovative collaborative planning framework for electric vehicle integrated charging and swapping stations (EVICSS) and DN for carbon emission reduction. Initially, the division of responsibilities and mechanism analysis for emission reduction in DN are presented. Subsequently, the ladder carbon price model is presented to incentivize carbon mitigation efforts. And, considering the architecture and functioning mode of the EVICSS, the operational model for EVICSS equipment is established to deliver high-quality services to EV users, taking into account fast charging stations (FCS), fast battery swapping stations (FBSS), and cascade energy storage system (CESS) comprehensively. Taking into account the economic implications of carbon trading, a collaborative planning strategy for EVICSS and the DN is formulated to minimize overall costs while maximizing carbon emission reductions. Then an modified integrated gravitational search algorithm and particle swarm optimization algorithm (MIGSA-PSOA) is customizedly developed to solve this complicated optimization problem. Finally, case studies based a real DN are conducted to illustrate the effectiveness of the collaborative planning model. The results demonstrated it can effectively respond to DN power regulation and realize carbon emission reduction. Compared with independent planning, collaborative planning can increase the planning cost and total cost to 15.6 % and 33.1 % respectively.

Data aggregation by enhanced squirrel search optimization algorithm for in wireless sensor networks

Data aggregation by enhanced squirrel search optimization algorithm for in wireless sensor networks

Implementing a smart city using internet of things based on wildwood combined with fractional order-based golden search algorithm.

The fast expansion of Internet of Things (IoT) devices in urban environments has resulted in a dramatic increase in both the volume and complexity of data produced, necessitating the implementation of sophisticated data analytics and machine learning methodologies to fully realize the advantages of smart cities. The incorporation of IoT sensors and devices has facilitated the establishment of extensive, dynamic, and diverse networks, which present considerable challenges for data analysis and decision-making processes. In response to these challenges, machine learning algorithms have surfaced as a feasible solution, capable of discerning intricate patterns and relationships within the data. Nonetheless, the efficacy of these algorithms is significantly influenced by the precise tuning of hyperparameters, a task that can be quite complicated, particularly within IoT-enabled smart cities. This study concentrates on the creation of an innovative optimization framework that integrates the WildWood algorithm with a fractional-order variant of the Golden Search Algorithm for hyperparameter optimization. The proposed framework is measured through simulations in a smart city traffic management background, resulting in notable reductions in latency (up to 30%), energy consumption (up to 25%), and enhancements in throughput (up to 20%) when compared to conventional optimization techniques. Moreover, the optimized WildWood model achieves a Mean Squared Error (MSE) of 0.85, indicating its proficiency in accurately forecasting traffic flow patterns. The results underscore the effectiveness of the proposed framework in enhancing the reliability, efficiency, and sustainability of IoT-enabled smart city systems.