<div>The integration of electric vehicle charging station (EVCS) and renewable distribution generation (RDG) in the grid affects the grid voltage, power losses, and system instability in the distribution system, therefore the article presents an approach for optimal placement and sizing of EVCS and RDG using an optimization approach named as modified particle swarm optimization (MOPSO) in radial distribution network (RDN). The efficacy of the optimization approach is demonstrated under both balanced and unbalanced dynamic load conditions in the IEEE 33-bus system. The influence of EVs and RDG on the RDN is analyzed by considering the maximum possible cases, e.g., 13 different scenarios, which replicate real-world scenarios. These results are validated using DIgSILENT Power Factory Software. The proposed research also covers Techno-Economic Assessment using HOMER software, which may enhance visibility of the renewable distribution generation importance in the current scenario.</div>

Increasing demand for renewable energy integration and efficient energy storage solutions have highlighted the critical role of battery. Batteries serve as essential components in energy systems, storing excess power for various applications, and backup power solution. However, achieving control for battery is challenging due to stability of charge and discharge, changing load condition, and battery state of charge fluctuation. To ensure efficiency of battery, accurate control of bi-directional converter is required. Bi-directional Converter facilitates the power flow required for this process but controlling battery charge discharge accurately. Among the many control methods, the Proportional-Integral (PI) controller is widely used for regulating the charge-discharge operation. However, selecting optimal PI parameters is non-trivial and greatly affects systems performance. This study proposes an enhanced control strategy for a bidirectional converter using PI controller optimized by a modified Particle swarm optimization (PSO) algorithm. The proposed method incorporates a dynamic re-randomized mechanism to overcome premature convergence in a standard PSO, improving its ability to escape local minima. Additionally, a penalty function is applied to restrict the search within a defined stable range for the controller gains. The performance of the system is evaluated based on the Integral of Time-Weighted Absolute Error (ITAE) criterion to minimize transient and steady-state errors. Simulation result using MATLAB/Simulink demonstrate that modified PSO-based PI controller significantly improves system performance-reducing overshoot, enchanting settling time, and maintaining stability under different operation modes (charge and discharge). This method offers a practical and efficient solution for optimizing converter control in battery-based energy storage systems.

Wildfires are among the most dangerous and least predictable natural hazards, necessitating continuous real-time monitoring of the advancing fire front. Traditional assets – such as satellite imagery or ground observation posts – often lack the responsiveness and completeness required for timely decision-making. A promising alternative is the use of a swarm of unmanned aerial vehicles (UAVs); however, effective coordination under dynamic conditions and constrained communication and computational resources calls for dedicated control algorithms. This work presents a multi-layer control strategy for a UAV swarm that integrates three components. Horizontal navigation is governed by the Artificial Potential Field (APF) method, which attracts agents to the fire-front line while repelling them from obstacles and neighboring vehicles. A distributed consensus protocol stabilizes flight at a common reference altitude, ensuring comparable viewing geometry. To achieve an even distribution along the front, a modified Particle Swarm Optimization (PSO) layer is employed, reducing competition between drones and unnecessary maneuvering. We report a series of computational experiments comparing classical APF with the hybrid APF+PSO scheme for minimizing a swarm motion performance functional. The hybrid approach lowers the objective by nearly an order of magnitude relative to APF alone, reduces behavioral variability, maintains a coordinated altitude without pronounced overshoot, and ensures reliable obstacle avoidance in the presence of a moving front. Minimum inter-drone separations did not fall below the 5-m safety threshold, confirming compliance with safety requirements. The algorithm sustains stable tracking of the moving front over the entire simulation horizon while preserving correct obstacle clearance. Overall, the proposed strategy combines computational simplicity with high reliability. Future work will incorporate onboard sensing (video and thermal cameras), modeling of wind and terrain effects, analysis of communication delays and losses, and extension of the approach to larger UAV teams.

ABSTRACT The growing energy demand has intensified reliability challenges in power distribution systems. This study employs network reconfiguration to minimize power loss, enhance voltage stability, and improve system reliability. A modified particle swarm optimization algorithm incorporating a chaotic map and a linearly decreasing inertia weight (PSO‐CLDIW) is proposed to address the limitations of conventional PSO. IEEE 33 and 69 bus systems were used to test the proposed method for power loss and reliability improvement. For the IEEE 33‐bus system, the power loss of PSO‐CLDIW decreased from 202.6771 to 139.5513 kW after reconfiguration under normal load. The reliability indices include SAIFI, SAIDI, CAIDI, ASAI, EENS, and AENS, with the corresponding values of 2.0261, 1.4291, 0.7053, 0.9998, 1522.683, and 0.0837, respectively. Under light load, PSO‐CLDIW achieved 33.433 kW loss compared to 47.071 kW in the base case, reflecting a 28.98% reduction. At heavy load, the power loss was 381.14 kW, resulting in 33.73% improvement. Reliability indices also showed significant enhancement, with SAIFI, SAIDI, CAIDI, EENS, and AENS values improving to 1.984, 1.368, 0.68953, 377.1413, and 0.020722, respectively, under light load, and 1.994, 1.386, 0.695, 3882.871, and 0.213 under heavy load. The IEEE 69‐bus system power loss decreased from 224.9606 to 98.5902 kW after reconfiguration under normal load, and SAIFI, SAIDI, CAIDI, ASAI, EENS, and AENS values are 1.112, 0.7613, 0.68464, 0.9999, 2913.084, and 0.2339, respectively, under normal load. PSO‐CLDIW achieved a power loss of 23.827 kW at light load, corresponding to a 53.83% reduction. Reliability indices improved, with SAIFI, SAIDI, CAIDI, ASAI, EENS, and AENS reaching 1.0246, 0.73701, 0.719321, 0.99992, 728.281, and 0.0585, respectively. At the heavy load, the power loss was 276.12 kW. Overall, the proposed PSO‐CLDIW method outperforms the baseline and other optimization techniques, demonstrating the superior ability of PSO‐CLDIW to minimize power loss, enhance reliability, and improve the voltage profile in distribution systems.

Fog computing has revolutionized the world by providing its services close to the user premises, which results in reducing the communication latency for many real-time applications. This communication latency has been a major constraint in cloud computing and ultimately causes user dissatisfaction due to slow response time. Many real-time applications like smart transportation, smart healthcare systems, smart cities, smart farming, video surveillance, and virtual and augmented reality are delay-sensitive real-time applications and require quick response times. The response delay in certain critical healthcare applications might cause serious loss to health patients. Therefore, by leveraging fog computing, a substantial portion of healthcare-related computational tasks can be offloaded to nearby fog nodes. This localized processing significantly reduces latency and enhances system availability, making it particularly advantageous for time-sensitive and mission-critical healthcare applications. Due to close proximity to end users, fog computing is considered to be the most suitable computing platform for real-time applications. However, fog devices are resource constrained and require proper resource management techniques for efficient resource utilization. This study presents an optimized resource allocation and scheduling framework for delay-sensitive healthcare applications using a Modified Particle Swarm Optimization (MPSO) algorithm. Using the iFogSim toolkit, the proposed technique was evaluated for many extensive simulations to obtain the desired results in terms of system response time, cost of execution and execution time. Experimental results demonstrate that the MPSO-based method reduces makespan by up to 8% and execution cost by up to 3% compared to existing metaheuristic algorithms, highlighting its effectiveness in enhancing overall fog computing performance for healthcare systems.

The article discusses the problem of synthesising optimal trajectories for moving load with a tower crane in order to increase its productivity and safety. A dynamic model of the system has been developed, including the boom, trolley and load suspended on a flexible rope, taking into account the pendulum oscillations of the load. To determine the laws of motion of the boom and trolley that ensure the specified load trajectory, the inverse kinematic problem has been solved. An optimisation approach has been proposed, aimed at minimising the duration of load transportation while complying with kinematic and dynamic constraints, in particular the maximum speeds of the trolley and boom rotation. To ensure smooth movement and reduce dynamic loads, regularisation methods are used to reduce the amplitude of load oscillations and eliminate unwanted changes in the direction of movement of the mechanisms. The numerical solution of the optimisation problem was performed using a modified particle swarm optimisation method (VCT-PSO), which demonstrated its effectiveness in selecting the optimal trajectory parameters. The influence of regularisation and the length of the flexible suspension on the dynamic characteristics of the system, in particular the amplitude of oscillations, peak forces and moments, as well as the duration of movement, was analysed. The results show that the use of regularisation significantly reduces dynamic loads and increases motion stability, although it increases transport time. Shortening the suspension length reduces motion time but can lead to an increase in oscillation amplitude. A new tool for analysing system dynamics in terms of deviations and velocity differences is proposed, which provides a visual assessment of the oscillation process and confirms the fulfilment of boundary conditions. The results obtained can be used to improve tower crane control systems and increase their efficiency on construction sites.

This study establishes a rigorous theoretical framework for Particle Swarm Optimization (PSO) convergence by introducing a novel symmetry assumption governing the algorithm’s stochastic components and a monotonicity condition between function values and Euclidean distance to the global optimum. Under this assumption, we prove linear convergence in expectation and almost sure linear convergence for a modified PSO algorithm with symmetric zero-mean random coefficients when parameters satisfy the explicit condition w+8(c12+c22)σr21−w<1. This provides the first closed-form relationship between inertia weight w, learning factors c1,c2, and random variance σr2 that guarantees convergence. Building on this theoretical foundation, we develop three hierarchical applications: (1) static parameter design that replaces empirical tuning with theoretical calculation from desired convergence rates; (2) symmetric random factor optimization that eliminates directional bias and stabilizes velocity dynamics while preserving exploration variance; and (3) dynamic adaptive strategies that adjust parameters in real-time based on particle dispersion feedback. By bridging the gap between empirical performance and theoretical guarantees, this work transforms PSO from an empirically driven heuristic into a provably convergent optimization tool with rigorous performance guarantees for objective functions satisfying strict monotonicity between fitness and distance to the optimum (e.g., strictly convex functions).

To achieve accurate path tracking for unmanned mining trucks when facing roads with a large range of continuous curvature changes, an improved linear quadratic regulator (ILQR) control method combining Fuzzy Logic-based Preview Distance Design (FBPD) and Adaptive Weight Matrix Design trained by Modified Particle Swarm Optimization (MPSO) is brought up in this study. The design of preview distance based on fuzzy logic considers road curvature and truck speed as inputs and the best preview distance as output. The Modified PSO method is adopted in this study to train the weight matrix of LQR under the conditions of different truck velocity intervals and road curvature intervals. The optimal weights under different path curvature intervals and truck velocity intervals are obtained, and finally made into two-dimensional look-up table to realize weight self-adaptation. Finally, the simulation test conducted on the truck whole dynamics model independently developed by Simulink and the real truck verification are used to compare the tracking effect of this algorithm with pure tracking and other algorithms. The algorithm shows good path tracking performance.

Improving PPP ambiguity resolution with a modified particle swarm optimization method

Efficient design of proton exchange membrane fuel cells (PEMFCs) requires balancing high electrical output with thermal stability, yet the complex interactions among operating parameters make this a challenging task. Addressing this gap, this study develops an integrated predictive–optimization–decision framework that systematically models PEMFC performance, explores trade-offs, and guides application-specific design choices. The primary innovation lies in combining multi-layer perceptron neural networks (MLPNN) with metaheuristic optimization, particle swarm optimization (PSO), modified particle swarm optimization (MPSO), multi-objective Harris hawks optimization (MOHHO), and multi-objective PSO (MOPSO), followed by decision-making using the additive ratio assessment (ARAS) method. Predictive modeling results demonstrate variable-specific advantages of optimization strategies: PSO-MLPNN yielded superior accuracy for electrical power output prediction (MAPE = 0.233%), while MPSO-MLPNN achieved marginally better accuracy for cell temperature prediction (MAPE = 0.301%). Multi-objective optimization revealed the inherent trade-off between power and temperature, with MOHHO providing broader Pareto fronts and greater diversity than MOPSO. Optimal operating conditions (STAn ≈ 2.0–2.15, STCa ≈ 2.1–2.3, RHCa ≈ 60–66%, Tin ≈ 26 °C) enabled peak power outputs near 5300 mW while maintaining stable cell temperatures around 39.5 °C. Finally, ARAS-based decision analysis identified seven design scenarios. The scenario with balanced weights yielded a cell power output of 5205.9 mW, representing an increase of approximately 6.94% compared to the mean cell power of 4867.9 mW in the dataset. The corresponding cell temperature was 39.53 °C, which is about 20.3% lower than the mean cell temperature of 49.61 °C. These results demonstrate the proposed framework’s ability to provide flexible and application-specific design strategies, simultaneously enhancing electrical performance and maintaining thermal stability and safety.

This paper presents an approach to modeling the movement of a multi-agent system in a two-dimensional space using a modified Particle Swarm Optimization (PSO) algorithm, adapted to account for the physical properties of the agents. The standard PSO, originally designed for solving optimization problems through swarm behavior, has been extended to simulate the motion of physical objects with defined mass, velocity, and inter-agent interactions. To ensure physically plausible motion and prevent collisions between agents, hybrid methods have been proposed that combine classical PSO with inter-particle potential functions. Trajectory planning and control over the direction and speed of agent movement have been governed by the modified PSOs, while collision avoidance is achieved through the influence of repulsive potential fields. Numerical simulations have been conducted to analyze the collective behavior of the swarm.

Classical time series methods are widely employed to analyze linear time series with a limited number of observations; however, their effectiveness relies on several strict assumptions. In contrast, artificial neural networks are particularly suitable for forecasting problems due to their data-driven nature and ability to address both linear and nonlinear challenges. Furthermore, recurrent neural networks feed the output back into the network as input, utilizing this feedback mechanism to enrich the information provided to the model. This study proposes a novel recurrent hybrid intuitionistic forecasting method utilizing a modified pi–sigma neural network, principal component analysis (PCA), and simple exponential smoothing (SES). In the proposed framework, lagged time series variables and principal components derived from the membership and non-membership values of an intuitionistic fuzzy clustering method are used as inputs. A modified particle swarm optimization (PSO) algorithm is employed to train this new hybrid network. By integrating PCA, modified pi–sigma neural networks (MPS-ANNs), and SES within a recurrent hybrid structure, the model simultaneously captures linear and nonlinear dynamics, thereby enhancing forecasting accuracy and stability. The performance of the proposed model is evaluated using diverse financial and environmental datasets, including CMC-Open (I–IV), NYC water consumption, OECD freshwater use, and ROW series. Comparative results indicate that the proposed method achieves superior accuracy and stability compared to other fuzzy-based approaches.

Accurate rainfall forecasting is vital for socio-economic planning in climate-sensitive regions. Traditional statistical models often fail to capture the non-linear and stochastic nature of rainfall. This paper conducts a systematic review of machine learning (ML) techniques applied to rainfall forecasting, covering 45 studies published between 2012 and 2024, following PRISMA guidelines. The analysis identifies four high-performing algorithms: Long Short-Term Memory (LSTM), Random Forest (RF), NeuralProphet, and Support Vector Machines (SVM). LSTM models optimized with Modified Particle Swarm Optimization (M-PSO) achieved the lowest Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). RF models demonstrated robustness for short-term forecasts, SVMs performed well with smaller datasets, and NeuralProphet offered explainability through a hybrid statistical–deep learning approach. Model choice depends on data characteristics, forecasting horizon, and the balance between accuracy and interpretability. The findings highlight the comparative strengths of these algorithms across different forecasting horizons.

Cloud computing has become the backbone of digital ecosystems, but growing workloads intensify challenges in resource optimization, virtual machine (VM) migration, and security assurance. Existing studies often address these issues in isolation, limiting their practical applicability. This paper presents a unified framework that integrates three complementary components: (i) an Improved Modified Particle Swarm Optimization (IMPSO) algorithm with adaptive inertia scheduling and dynamic mutation control, which outperforms IPSO in convergence speed and load distribution accuracy; (ii) a machine learning–assisted hybrid live VM migration method with dirty-page clustering and workload prediction to minimize downtime; and (iii) a blockchain-enabled secure migration layer to ensure tamper-proof and auditable state transfer. The revised version of this study includes statistical validation (confidence intervals, t-tests) and attack simulation experiments (e.g., man-in-the-middle and replay attacks) to ensure methodological rigor and realistic security assessment. Experimental results on a real XenServer testbed show that the proposed system improves response time by ~30%, reduces migration downtime by ~60%, and ensures 100% migration integrity with ?15% security overhead. Overall, this work represents among the first unified frameworks that jointly optimize resource allocation, downtime reduction, and blockchain-based security in a practically validated, end-to-end cloud migration environment.

Mobile robots are increasingly integral to diverse applications, with path-planning algorithms being essential for efficient and secure mobile robot navigation. Mobile robot path planning is defined as the design of the least time-consuming, shortest-distance, and most collision-free path from the starting point to the endpoint for the mobile robot’s autonomous movement. This study investigates and assesses two widely used algorithms in artificial intelligence (AI)—Improved Particle Swarm Optimization (IPSO) and Improved Genetic Algorithm (IGA)—for path planning of mobile robot navigation problems. In this work Manhattan movements are proposed as a distance formula to modify both algorithms in the path planning of the mobile robot navigation problem. Unlike the traditional GA and PSO, which can use horizontal search, the proposed algorithm relies on vertical search, which gives us an advantage. The results demonstrate the effectiveness of these modified algorithms in barrier detection and obstacle avoidance. Six different experiments were run using both improved algorithms to show their ability to achieve their goal and avoid obstacles in various scenarios with different complexities. Across various scenarios, the tested AI algorithms performed effectively, regardless of the map scale and complexity. This paper proposes a complete comparison between the two improved algorithms in different scenarios. The results show that the algorithms’ performance is influenced more by the density of walls and obstacles than by the size or complexity of the map.

This paper proposes a hybrid maximum power point tracking (MPPT) controller that integrates Modified Particle Swarm Optimization (MPSO) with Adaptive Fuzzy Logic Control (AFLC) for robust and efficient power tracking under partial shading conditions (PSC). The MPSO component initially explores the global search space to locate the approximate MPP, effectively navigating through the local MPPs. Once the MPP is identified, the AFLC component fine-tunes the duty cycle using linguistic rules, ensuring rapid convergence to the global MPP with minimal oscillations. MATLAB/Simulink tests across five different partial shading patterns demonstrated that the MPSO-AFLC achieves a tracking efficiency of 99.92% ± 0.03%, convergence times between 0.006 and 0.011 s, an average settling time ≤ 0.011 s, and steady-state power oscillations below 5 W. When compared to meta-heuristic algorithms (MPSO, CSA, and GWO) and five recent hybrid methods, the proposed controller demonstrates superior robustness, faster convergence, and smaller steady-state oscillations.

The increasing integration of renewable energy sources, particularly photovoltaic (PV) systems, poses significant challenges in the Unit Commitment (UC) problem due to their intermittent and inertial nature. This condition can cause frequency instability during system disturbances, necessitating the development of new strategies to maintain reliable power system operation. This study proposes an enhanced UC optimization framework by integrating conventional thermal generating units, PV plants, and energy storage systems (ESS) that act as virtual inertia providers. To solve the optimization problem while considering various technical constraints—such as ramping limits, minimum on/off times, rotating reserve requirements, and nadir frequency thresholds—a modified Particle Swarm Optimization (PSO) algorithm is employed. The model is tested on a generating system consisting of nine thermal units, one PV plant, and one ESS. Simulation results show that the proposed method is capable of maintaining the system frequency above the nadir threshold of 49.5 Hz during disturbances while minimizing the total operating cost. Specifically, the optimal configurations without nadir constraints and with ESS integration achieve convergence in only four iterations with a computational time of 1.9 seconds. These findings demonstrate the effectiveness of integrating ESS as virtual inertia and the efficiency of a modified PSO algorithm in handling UC in systems with high renewable energy penetration. This framework offers a promising approach to improving cost efficiency and frequency stability in future renewable energy-based power systems.

BackgroundIdentifying the Non-Alcoholic Steatohepatitis (NASH) that can cause liver failure-based morbidity remains a challenging research problem since there is no confirmed and effective approach for its early and accurate diagnosis yet. A large amount of medical data is collected to diagnose the NASH where the majority of them are redundant.MethodsThis paper initially focuses on selecting the most informative blood test data among the collected big data with the Pearson correlation statistical approach and modified Particle Swarm Optimization with Artificial Neural Networks (PSO-ANN) machine learning algorithm. Then, a gradient based Batch Least Squares (BLS) and a search-based Artificial Bee Colony (ABC) machine learning algorithms are implemented to optimize the NASH prediction models. Confirmed operational NASH diagnosis supervise the statistical and machine learning algorithms to develop accurate prediction models.ResultsTwo machine learning algorithms were trained and also validated with the varying number of selected input features. The results yielded that the trained BLS machine learning model is able to diagnose benign and malignant cases with 100% and 98% accuracies, respectively. The trained ABC machine learning algorithm diagnoses the benign and malignant cases with 90.5% and 94.3% accuracies, respectively.

Particle Swarm Optimization (PSO) is a metaheuristic optimization technique based on population behavior, inspired by the movement of a flock of birds or a school of fish. In this method, particles move in a search space to find the global minimum of an objective function. In this work, a modified PSO algorithm written in Fortran 90 is proposed. The optimized structures obtained with this algorithm are compared with those obtained using the basin-hopping (BH) method written in Python (3.10), and complemented with density functional theory (DFT) calculations using the Gaussian 09 software. Additionally, the results are compared with the structural parameters reported from single crystal X-ray diffraction data for carbon clusters Cn(n = 3–5), and tungsten–oxygen clusters, WOnm−(n = 4–6, m=2,4,6). The PSO algorithm performs the search for the minimum energy of a harmonic potential function in a hyperdimensional space ∈R3N (where N is the number of atoms in the system), updating the global best position ( gbest) and local best position ( pbest), as well as the velocity and position vectors for each swarm cluster. A good approximation of the optimized structures and energies of these clusters was obtained, compared to the geometric optimization and single-point electronic energies calculated with the BH and DFT methods in the Gaussian 09 software. These results suggest that the PSO method, due to its low computational cost, could be useful for approximating a molecular structure associated with the global minimum of potential energy, accelerating the prediction of the most stable configuration or conformation, prior to ab initio electronic structure calculation.

The issue of sensor coverage in Wireless Sensor Networks (WSNs) is crucial, particularly as these networks are deployed in military applications for the armed forces as well as in civilian health applications. Therefore, improving coverage and communication while minimizing interference between sensors is essential. This paper presents a hybrid meta-heuristic approach to optimizing node deployment in WSNs using a modified Particle Swarm Optimization (mPSO) and Ant Lion Optimization (ALO) algorithms. The Particle Swarm Optimization (PSO) algorithm was applied for global search, while the ALO focused on internal search within the Region ofInterest (ROI). Initially, nodes are deployed randomly within the ROI. The algorithm then detects uncovered gaps and iteratively enhances node placement, leading to an improved coverage ratio and minimized node overlap. The results of the hybrid meta-heuristic algorithm show improved performance compared to using PSO and ALO separately. This approach leads to an enhanced network lifetime and energy consumption of the WSN.