Wolf Research Articles

Effect of DG penetration on hybrid relay coordination using user-defined dual-setting directional overcurrent relays and distance relays

ABSTRACT The efficient coordination of the distance and directional overcurrent relays (DOCRs) is jeopardized by the massive deployment of renewable distributed generation (DG) into electrical power networks. The two key aspects influencing the relay coordination are the bidirectional flow of current and increased short-circuit currents due to DG integration. This study investigates the consequences of variable DG penetration on the distance and dual-setting DOCRs (DS-DOCRs) coordination. As a result, common optimal relay settings have been obtained that can be utilized for variable DG penetration levels in modified IEEE-14 bus test system. For the distance relays (DRs), a fixed zone 1 and variable zone 2 operation have been considered. The proposed combined protection scheme is tested on a modified IEEE-14 bus test system using DS-DOCRs and DRs. The relay coordination problem is formulated as a constrained non-linear optimization problem and solved by genetic algorithm (GA) and gray wolf optimization (GWO). In this paper, DS-DOCRs with user-defined relay characteristics have demonstrated superior performance in line protection compared to conventional DOCRs with normal inverse (NI) characteristics. In addition, a comprehensive comparative analysis of optimization algorithms has been performed between GA and GWO algorithms.

A Methodology to Optimize PMSM Driven Solar Water Pumps Using a Hybrid MPPT Approach in Partially Shaded Conditions

Solar water pumps are crucial for farmers, significantly reducing energy costs and providing independence from conventional fuels. Their adoption is further incentivized by government subsidies, making them a practical choice that aligns with sustainable agricultural practices. However, the cost of the required solar panels for the chosen power makes it essential to optimize solar water pumping systems (SWPS) for economic viability. This study enhances the efficiency and reliability of permanent magnet synchronous motor (PMSM)-driven SWPS in rural areas using hybrid maximum power point tracking (MPPT) algorithms and voltage-to-frequency (V/f) control strategy. It investigates the sensorless scalar control method for PMSM-based water pumps and evaluates various MPPT algorithms, including grey wolf optimization (GWO), particle swarm optimization (PSO), perturb and observe (PO), and incremental conductance (INC), along with hybrid combinations. The study, conducted using MATLAB Simulink, assesses these algorithms on convergence time, MPPT accuracy, torque ripple, and system efficiency under different partial shading conditions. Findings reveal that INC-GWO excels, providing higher accuracy, faster convergence, and reduced steady-state oscillations, thus boosting system efficiency. The V/f control strategy simplifies control mechanisms and enhances performance. Considering system non-idealities and maximum duty cycle limitations, PMSM-based SWPS achieve superior efficiency and stability, making them viable for off-grid water pumping applications.

VMD-ATT-LSTM electricity price prediction based on grey wolf optimization algorithm in electricity markets considering renewable energy

Electricity price prediction is essential for the optimal dispatch in power markets, with accurate prediction models being critical for efficient power system operations and market trading decisions. Deep learning networks, with their powerful nonlinear modeling capabilities, have shown promising results in electricity price forecasting. However, their design techniques, especially the selection of network parameters, remain challenging. This indicates that the optimization and exploration of deep learning networks in electricity price forecasting models require further investigation. This paper innovatively proposes a forecasting model that uniquely integrates Variational Mode Decomposition (VMD), Grey Wolf Optimization (GWO), Attention Mechanism (ATT), and Long Short-Term Memory Network (LSTM), optimizing the model from three different perspectives. First, during the data preprocessing phase, the training set is subjected to VMD to reduce noise, thereby enhancing the capture of multi-scale characteristics inherent in electricity price time series. The ATT layer is integrated to adaptively allocate weights, enhancing the model's focus on significant features. The GWO is applied to optimize hyperparameters of the LSTM, accelerating convergence and improving iteration accuracy, thereby reducing model error. A series of experiments were conducted using multiple regional electricity price datasets, evaluated with several metrics including RMSE. The results validated the effectiveness of the proposed three modules in improving the performance of the time series network, with VMD making the most significant contribution. Among all models, VMD-GWO-ATT-LSTM consistently outperformed others, demonstrating its effectiveness and robustness in electricity price forecasting.

Particle swarm optimization based on data driven for EV charging station siting

Charging stations are an important support facility for electric vehicles (EVs). Nowadays, the EV industry is developing rapidly, however, the imperfect construction of charging stations or the unreasonable choice of location has seriously reduced the desire of people to buy EVs and led to the problem of difficult charging of EVs in many areas. At present, the research field of EV charging station siting suffers from the inability to quickly and accurately calculate the optimal solution for charging station siting. In this regard, a particle swarm optimization based on deep neural networks modified boundaries (DNNMBPSO) is proposed for solving the problem. DNNMBPSO reduces the convergence value of the objective function by applying deep learning to modify the boundary of the particle swarm optimization. DNNMBPSO is an algorithm that combines heuristic and data driven. In this study, DNNMBPSO is applied for siting study in a system having 50 alternative points, 500 alternative points, and 1000 alternative points and a case of siting of electric vehicle charging stations in Nanning, Guangxi, China. The convergence value of the DNNMBPSO-based objective function is found to be at least 5.5 %, 1.7 %, 8.23 % and 14.7 %, lower compared to genetic algorithms, African vulture optimization algorithm, particle swarm optimization, and grey wolf optimization algorithms, respectively. Traditional heuristic optimization algorithms cannot find optimal solutions in large-scale systems, while DNNMBPSO shows feasibility in large-scale systems.

Effective clinical decision support implementation using a multi filter and wrapper optimisation model for Internet of Things based healthcare data

Feature Selection (FS) is essential in the Internet of Things (IoT)-based Clinical Decision Support Systems (CDSS) to improve the accuracy and efficiency of the system. With the increasing number of sensors and devices used in healthcare, the volume of data generated is vast and complex. Relevant FS from this data is crucial in reducing computational overhead, improving the system’s interpretability, and enhancing the Decision-Making System (DMS) quality. FS also aids in addressing the problems of data redundancy and noise, which can negatively impact the system’s performance. FS is critical to developing practical and dependable CDSS in IoT-based healthcare sectors. This research proposes a two-phase FS model. Phase-I employs an ensemble of five Filter Methods (FM), followed by a Pearson Correlation Method (PCM). Phase-II uses the Binary Optimized Genetic Grey Wolf Optimization Algorithm (BOGGWOA) as a Wrapper Method (WM). This recommended model integrates the most valuable features of each filter. Then, it uses the Pearson Correlation Coefficient (PCC) to get rid of features that aren’t needed, a Support Vector Machine (SVM) to guess how accurate their classification will be, and BOGGWOA as the Wrapper Method (WM) to pick the most essential features with the best CA.

State of Health Estimation of Lithium‐Ion Batteries Based on Differential Thermal Voltammetry and Improved Gray Wolf Optimizer Optimizing Gaussian Process Regression

Accurate estimation of the state of health (SOH) of lithium‐ion batteries (LIBs) is essential for their safe operation. Therefore, herein, a novel approach that combines Gaussian process regression (GPR) optimized using an improved gray wolf optimizer (IGWO) with differential thermal voltammetry (DTV) is introduced. In this approach, the peak and valley information of the DTV curves are used to reveal the battery‐aging mechanisms, with the slopes and durations between peaks and valleys used as health characteristics. The correlation between the characteristics and SOH of the battery is analyzed to build a health feature dataset. IGWO optimizes the GPR hyperparameters to address their dependence on the initial values and susceptibility to local optimization and employs a dimension‐learning strategy to enhance the population diversity and prevent premature convergence. DTV curves and an IGWO‐GPR model for SOH estimation using four cells from the NASA LIB public aging dataset are developed and validated. The results show root mean square errors below 0.007 and mean absolute errors under 0.006 for all cells. The coefficient of determination exceeds 0.92 for three cells, with one battery exhibiting a value of 0.866. This method provides accurate and efficient SOH estimation, essential for safe battery operation.

Constrained H∞ control with gain switching for a nonlinear active suspension system matching non-pneumatic wheel

In this study, a constrained H ∞ controller with gain switching is put forward for the active suspension system to improve the overall performance of vehicles equipped with non-pneumatic wheels, considering the nonlinearity of wheel stiffness, actuator saturation, and output constraints. Firstly, a quarter-vehicle model incorporating active suspension and non-pneumatic wheel (NPW) is established experimentally. Secondly, the system model is linearized using Taylor series expansion and linear fractional transformation (LFT). A constrained H ∞ control strategy and a gain switching method based on road classification are proposed, taking into account the parameter uncertainty in linearization process and the variation of performance demands under different road conditions. Then, an L ∞ state observer is designed for the required system state, and the road roughness classifier based on grey wolf optimization (GWO) and probabilistic neural network (PNN) is developed to obtain the necessary road information. A bench test is finally performed using the reconstructed actual road as input. The test results validate the effectiveness and superiority of the proposed control strategy.

Evaluating the impact of improved filter-wrapper input variable selection on long-term runoff forecasting using local and global climate information

Long-term runoff forecasting (LRF) is great important for water resources management. Employing accurate local and global climate information can significantly enhance the accuracy of LRF. The filter-wrapper input variables selection (FWIVS) method can efficiently select local and global climate indices for LRF. However, binary metaheuristic algorithms (BMAs) in wrapper input variable selection (WIVS), such as golden jackal optimization (GJO) and gray wolf optimizer (GWO), frequently encounter local optima, which significantly impact LRF accuracy and remain unexplored. Additionally, previous FWIVS methods overlooked physical relationship between local and global climate information. Consequently, an improved GJO (IGJO) that considers the complementarity of local weather and global climate indices and prevents local optima was proposed. Four machine learning models and an integrated model (IM) were used as learning models for WIVS. Finally, eight BMAs, including IGJO, improved GWO and so on, were constructed and integrated with five learning models to develop forty wrappers for evaluating impact of various BMAs and models on WIVS and LRF. The Jinsha River was served as a case study. Results demonstrated that the impact of the improved BMAs on wrapper fitness and variables selection was higher than learning model. IGJO retained critical variables for WIVS, especially local weather variables. Moreover, IGJO effectively reduced redundant information and extracted more robust complementary global climate indices for WIVS. In addition, LSTM-IGJO exhibited the greatest enhancement in wrapper fitness and LRF accuracy, achieving a NSE of 0.92 and a MAE of 575.83 m3/s. Specifically, this finding indicated that selecting the key variables and selecting the stronger complementary global climate indices instead the redundant local weather variables for retaining key information, while eliminating redundant information, can efficiently improve the LRF accuracy.

An effective binary dynamic grey wolf optimization algorithm for the 0-1 knapsack problem

An effective binary dynamic grey wolf optimization algorithm for the 0-1 knapsack problem

Enterprise supply chain network optimization algorithm based on blockchain-distributed technology under the background of digital economy

Demand forecasting is essential for streamlining supply chain operations in the digital economy and exceeding customer expectations. On the other hand, traditional forecasting techniques cannot frequently present real-time data and respond to dynamic changes in the supply chain network, leading to less-than-ideal decision-making and higher costs. This research aims to create a technique for optimizing the supply chain network based on blockchain-distributed technology (SCN-BT) to overcome these drawbacks and fully utilize the potential of the digital economy. The suggested framework uses the hybridized LSTM network and Grey Wolf Optimization (GWO) algorithm to examine demand forecasting in the supply chain network for inventory planning. The SCN-BT framework develops a safe and productive, enabling precise and flexible demand by combining blockchain with optimization techniques. A thorough case study utilized information collected from an enterprise supply chain that operates in the digital economy to show the efficiency of the suggested framework. Compared to conventional approaches, the results show considerable gains in demand forecasting precision, responsiveness of the supply chain, and cost-effectiveness. In the context of the digital economy, demand sensing and prediction enable firms to react to changes swiftly, shorten turnaround times, optimize inventory levels, and improve overall supply chain performance. The results highlight how blockchain technology has the potential to enhance collaboration, trust, and transparency inside intricate supply chain networks working in the digital economy. The experimental results show the proposed to achieve prediction rate of demand prediction rate of 128.93, demand forecasting accuracy ratio of 92.18%, optimum efficiency of 94.25%, RMSE rate of 1841.25, MAE rate of 260.74, and sMAPE rate of 0.1002 compared to other methods.

Neutrosophic goal programming technique with bio inspired algorithms for crop land allocation problem

In agriculture, crop planning and land distribution have been important research subjects. The distribution of land involves several multi-functional tasks, such as maximizing output and profit and minimizing costs. These functions are influenced by a variety of uncertain elements, including yield, crop price, and indeterminate factors like seed growth and suitable fertilizer. In order to address this problem, other researchers have used fuzzy and intuitionistic fuzzy optimization approaches, which did not include the indeterminacy membership functions. However, the neutrosophic optimization technique addresses the problem by using individual truth, falsity, and indeterminacy membership functions. So, to improve the optimal solution, the Neutrosophic Goal Programming (NGP) problem with hexagonal intuitionistic parameters is employed in this study. The membership functions for truth, indeterminacy, and falsity are constructed using hyperbolic, exponential, and linear membership functions. Minimizing the under deviations of truth, over deviations of indeterminacy, and falsity yields the NGP achievement function, which is used to attain optimal expenditure, production, and profit under the constraints of labour, land, food requirements, and water. Bio-inspired computing has been a major research topic in recent years. Optimization is mostly accomplished through the use of bio-inspired algorithms, which draw inspiration from natural behaviour. Bio-inspired algorithms are highly efficient in exploring large solution spaces, and helps to manage trade-offs between various goals, and providing the global optimal solution. Consequently, bio-inspired algorithms such as Grey Wolf Optimization (GWO), Social Group Optimization (SGO), and Particle Swarm Optimization (PSO) are employed in the current work to determine the global optimal solutions for the NGP achievement function. The data for the study was collected from the medium-sized farmers in Ariyalur District, Tamil Nadu, India. To illustrate the uniqueness and application of the developed method, the optimal solutions of the suggested method are compared with Zimmermann, Angelov, and Torabi techniques. The proposed technique demonstrates that the bioinspired algorithms’ optimal solution to the neutrosophic goal is superior to the existing approaches.

Large-scale magnetic target state estimation using model parameter optimization

Abstract Aiming at the problem of non-negligible target scale in the state estimation of magnetic targets, a state estimation method that requires only the measurement data of a single three-axis magnetic sensor and is insensitive to the initial value is proposed. Firstly, the state estimation model of a single three-component magnetic sensor is established based on a magnetic dipole array. A signal preprocessing method is designed to reject useless signals and keep the waveform intact. Five swarm intelligent optimization algorithms such as Particle Swarm Optimization (PSO), Artificial Hummingbird Algorithm (AHA), Artificial Rabbits Optimization (ARO), Grey Wolf Optimizer (GWO), and Improved GWO (IGWO) are introduced to perform state optimization, and two methods, such as Conjugate Gradient Least Squares (CGLS), and Stepwise Regression (SR), are introduced to calculate the magnetic moment parameters, and PSO-CGLS, AHA-CGLS, AHA-CGLS, ARO-CGLS, ARO-CGLS, ARO-CGLS, ARO-CGLS, ARO-CGLS, ARO-CGLS, ARO-CGLS, ARO-CGLS, and ARO-CGLS are designed in combination. CGLS, ARO-CGLS, GWO-CGLS, IGWO-SR, IGWO-CGLS, and six state estimation methods. In order to address the problem that the parameter optimization range is too large, the state to be estimated is adjusted from the initial state to the state at the moment of the maximum value of the magnetic field modulus, and the method of positive transverse distance estimation is used to narrow the range of positive transverse position optimization. Finally, numerical simulation tests and ship model tests are used for verification, and the results show that the proposed methods are accurate and can meet the needs of precise target state estimation.

A crack identification scheme based on neural network surrogate model and XFEM

Crack detection and identification is of great significance to the safety issues of engineering structures. In this paper, an intelligent crack identification scheme based on extended finite element and neural network surrogate model is proposed to realize the accurate identification of crack parameters. The method firstly employs extended finite element forward analysis to obtain the displacement data of measurement points on geometric models with different crack lengths, and inputs them as sample data to train the agent model, establishes a neural network-based inverse analysis model for crack identification, and automatically updates the threshold and weight of the neural network by using the Gray Wolf optimization algorithm to finally compute the globally optimal results. In the screening of the surrogate model, this paper verifies the advantages of the neural network surrogate model in data fitting and crack information extraction by comparing and analyzing the characteristics of neural network, support vector machine and other surrogate models, and optimizing the neural network surrogate model by adopting the Gray Wolf optimization algorithm. Finally, several numerical examples of different types of cracks are given to verify the validity of the proposed method, and the results show that the proposed method can accurately invert the geometric information of cracks.

Local population dynamics of gray wolves Canis lupus and Eurasian lynx Lynx lynx exhibit consistency with intraspecific contest competition models

AbstractIn Europe, the gray wolf and Eurasian lynx populations are recovering after various levels of persecution. The two species differ in their social structure and spatial patterns of aggregation. Using model selection, we investigated the consistency of the available time series data on local wolf and lynx sub‐populations with a number of single‐species population growth models that pertain to two types of intraspecific competition, namely, scramble (SC) and contest competition (CC), and reflect random (R) or aggregated (A) distribution of individuals. The applied models of population growth—the Ricker (SCR), Skellam (CCR), Hassell (SCA), and Beverton–Holt (CCA) models—were all parameterized in terms of intrinsic growth rate and carrying capacity with unified definitions. The projected carrying capacity was allowed to show a temporal trend, which was justified by an observed increase in prey abundance in recent decades. For both species, the models pertaining to contest competition outperformed the scramble competition models, and the Beverton–Holt model had the greatest weight. However, for the lynx, the difference of performance between the scramble and contest competition models was considerably smaller than that for the wolves. In most of the models, when it was meaningful, an optional time lag operator was added to account for a delay in individual maturity and reproduction. However, the models with a time lag had a worse fit than the models without it. This study promotes the application of population models that reflect intraspecific competition for modeling population dynamics in a single‐ or multi‐species framework.

Optimization of Operation Strategy of Multi-Islanding Microgrid Based on Double-Layer Objective

The shared energy storage device acts as an energy hub between multiple microgrids to better play the complementary characteristics of the microgrid power cycle. In this paper, the cooperative operation process of shared energy storage participating in multiple island microgrid systems is researched, and the two-stage research on multi-microgrid operation mode and shared energy storage optimization service cost is focused on. In the first stage, the output of each subject is determined with the goal of profit optimization and optimal energy storage capacity, and the modified grey wolf algorithm is used to solve the problem. In the second stage, the income distribution problem is transformed into a negotiation bargaining process. The island microgrid and the shared energy storage are the two sides of the game. Combined with the non-cooperative game theory, the alternating direction multiplier method is used to reduce the shared energy storage service cost. The simulation results show that shared energy storage can optimize the allocation of multi-party resources by flexibly adjusting the control mode, improving the efficiency of resource utilization while improving the consumption of renewable energy, meeting the power demand of all parties, and realizing the sharing of energy storage resources. Simulation results show that compared with the traditional PSO algorithm, the iterative times of the GWO algorithm proposed in this paper are reduced by 35.62%, and the calculation time is shortened by 34.34%. Compared with the common GWO algorithm, the number of iterations is reduced by 18.97%, and the calculation time is shortened by 22.31%.

Revolutionizing PV grid integration: Metaheuristic optimization of fractional PI controllers in T-type neutral point piloted inverters for enhanced performance

This study investigates the efficacy of FOPI regulators as a substitute for conventional proportional integral (PI) controllers in grid-connected PV inverters. The research's objective is to improve the dynamic efficiency of these systems by integrating intelligent optimization techniques that utilize both PI and FOPI controllers and employing different metaheuristic optimization procedures. The study introduces four new optimization algorithms: the Tyrannosaurus Optimization Algorithm (TROA), the Nutcracker Optimization Algorithm (NOA), the Golden Eagle Optimizer (GEO), and the Jellyfish Search Optimizer (JSO). These are made to meet the needs of multi-objective optimization. The proposal suggests using two PI/FOPI regulators to regulate both voltage and amperage provided by the multilayer inverter. The proposal employs a T-type three-level inverter, known for its superior conversion efficiency over conventional inverters. Matlab-Simulink simulations demonstrate that the Nutcracker optimization algorithm (NOA) outperforms other metaheuristic techniques for optimizing dynamic behavior, such as overshoot, settling time, execution, and rising time. Comparisons with existing methods, such as the Manta Rays Foraging Optimization (MRFO) and Grey Wolf Optimizer (GWO), show that all four new algorithms consistently outperform these existing algorithms. The data suggest that using NOA improves stability, efficiency, and power factor while reducing the inverter's THD.

A Novel Short-Term PM2.5 Forecasting Approach Using Secondary Decomposition and a Hybrid Deep Learning Model

PM2.5 pollution poses an important threat to the atmospheric environment and human health. To precisely forecast PM2.5 concentration, this study presents an innovative combined model: EMD-SE-GWO-VMD-ZCR-CNN-LSTM. First, empirical mode decomposition (EMD) is used to decompose PM2.5, and sample entropy (SE) is used to assess the subsequence complexity. Secondly, the hyperparameters of variational mode decomposition (VMD) are optimized by Gray Wolf Optimization (GWO) algorithm, and the complex subsequences are decomposed twice. Next, the sequences are divided into high-frequency and low-frequency parts by using the zero crossing rate (ZCR); the high-frequency sequences are predicted by a convolutional neural network (CNN), and the low-frequency sequences are predicted by a long short-term memory network (LSTM). Finally, the predicted values of the high-frequency and low-frequency sequences are reconstructed to obtain the final results. The experiment was conducted based on the data of 1009A, 1010A, and 1011A from three air quality monitoring stations in the Beijing area. The results indicate that the R2 value of the designed model increased by 2.63%, 0.59%, and 1.88% on average in the three air quality monitoring stations, respectively, compared with the other single model and the mixed model, which verified the significant advantages of the proposed model.

Isotope values reveal “canopy effect” in deer territoriality and maize consumption for dogs from archaeological sites in Kentucky dating to the Middle Woodland through Late Fort Ancient time periods

This research analyzes stable carbon, nitrogen, and oxygen isotope values in tooth collagen and enamel to investigate foraging and territorial behavior in white-tailed deer (Odocoileus virginianus Zimmermann) and maize (Zea mays Linneaus) consumption in dogs (Canis familiaris Linneaus). The study analyzed 22 deer teeth from 13 archaeological sites in Kentucky covering a span of approximately 1,500 years of human occupation. The article presents evidence of foraging and territorial behavior in white-tailed deer, identified through the “canopy effect” observed in deer stable carbon isotope values in remains spanning from the Middle Woodland (200 BCE – CE 500) to Late Fort Ancient (CE 1400 – 1680) time periods in Kentucky. Additionally, teeth samples from nine dog and one wolf (Canis lupus Linneaus) were analyzed and indicate significant consumption of maize in seven of the dog samples. These specimens came from seven archaeological sites in Kentucky dating from the Early through Late Fort Ancient (CE 1400 – 1680) time periods. The study also contributes to the growing database of isotope studies in the Eastern Woodlands by presenting carbon and nitrogen isotope values on deer bone collagen from nine deer bone samples from three of the same archaeological sites dating to the Middle Woodland to Early Late Woodland.

A novel hybrid deep learning approach with GWO–WOA optimization technique for human activity recognition

The effectiveness of Human Activity Recognition (HAR) models can be largely attributed to the components derived from domain expertise. The classification system swiftly and effectively categorizes human physical activity by utilizing a comprehensive collection of variables. To construct HAR models and categorize different activities, deep learning algorithms have recently seen increased application in academic research for autonomously extracting features from raw sensory data. The primary goal of this study is to develop a strong and accurate activity classification model by first extracting features from an input dataset and then using deep learning models. In this research, we look at how well the model does in the field of HAR. Analyzing time-series data from smartphones and wearable sensors, algorithms based on deep learning (DL) have been used to forecast various human actions. Applying DL-based methods to time-series data presents a variety of challenges, notwithstanding their usage for activity identification. If the suggested approach is put into practice, the concerns mentioned before may be alleviated. To construct HAR classification techniques using data collected from wearable sensors, this study presents two Hybrid Learning Algorithms (HLA). This research employs Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) methods to teach the model sequential and spatial patterns. The process of selecting characteristics has been enhanced through the use of optimization techniques. Together, the Whale Optimization Algorithm and the Grey Wolf Optimizer form a Hybrid Optimization approach, which is introduced in this study. By combining and capitalizing the benefits of both approaches, the hybrid technique enhances the optimization process as a whole. This research may also assist individuals who have undergone amputations or experienced strokes in selecting an appropriate model and developing a personalized gait reference trajectory.

Exploring the potential of 5G uplink communication: Synergistic integration of joint power control, user grouping, and multi-learning Grey Wolf Optimizer

Non-orthogonal Multiple Access (NOMA) techniques offer potential enhancements in spectral efficiency for 5G and 6G wireless networks, facilitating broader network access. Central to realizing optimal system performance are factors like joint power control, user grouping, and decoding order. This study investigates power control and user grouping to optimize spectral efficiency in NOMA uplink systems, aiming to reduce computational difficulty. While previous research on this integrated optimization has identified several near-optimal solutions, they often come with considerable system and computational overheads. To address this, this study employed an improved Grey Wolf Optimizer (GWO), a nature-inspired metaheuristic optimization method. Although GWO is effective, it can sometimes converge prematurely and might lack diversity. To enhance its performance, this study introduces a new version of GWO, integrating Competitive Learning, Q-learning, and Greedy Selection. Competitive learning adopts agent competition, balancing exploration and exploitation and preserving diversity. Q-learning guides the search based on past experiences, enhancing adaptability and preventing redundant exploration of sub-optimal regions. Greedy selection ensures the retention of the best solutions after each iteration. The synergistic integration of these three components substantially enhances the performance of the standard GWO. This algorithm was used to manage power and user-grouping in NOMA systems, aiming to strengthen system performance while restricting computational demands. The effectiveness of the proposed algorithm was validated through numerical evaluations. Simulated outcomes revealed that when applied to the joint challenge in NOMA uplink systems, it surpasses the spectral efficiency of conventional orthogonal multiple access. Moreover, the proposed approach demonstrated superior performance compared to the standard GWO and other state-of-the-art algorithms, achieving reduced system complexity under identical constraints.