Water is essential for ecological sustainability and human survival, necessitating effective management to meet rising global demands and address climate change. Traditional water supply monitoring methods are labor-intensive and slow, limiting real-time data acquisition and issue resolution. This paper presents QoW-Pro, an IoT-based water monitoring system that leverages AI algorithms to significantly enhance water quality assessments and leak detection. QoW-Pro enables real-time data collection, predictive modeling, and anomaly detection, leading to improved decision-making in water resource management. The system demonstrates quantitative improvements in leak detection accuracy and water quality prediction, offering a scalable solution adaptable to both urban and agricultural settings. By combining IoT and AI, this research contributes to the sustainable management of water resources, ensuring their availability and quality for future generations.
13 June 2025 in International Journal of Networked and Distributed Computing
The study addresses the Multiple Depot Vehicle Routing Problem (MDVRPTW) challenge, focusing on optimizing pathways for a fleet of vehicles to distribute goods to customers while adhering to delivery window constraints. The study introduces a new category, Green MDVRPTW, which aims to reduce environmental impact through innovative approaches. By combining machine learning and genetic algorithms, the research optimizes routing decisions to minimize journey costs, fleet size and aggregate delays. The use of clustering techniques to group clients based on depot proximity enhances routing efficiency. The paper employs a Tuned Genetic Algorithm and metaheuristics to tackle the Green MDVRPTW problem effectively. Furthermore, the paper provides a comprehensive overview of MDVRPTW solutions, presents a mathematical model for Green MDVRPTW, and details the implementation of the Tuned Genetic Algorithm and clustering concepts. Computational outcomes are analyzed against benchmark standards. The research contributes valuable insights for sustainable transportation planning and optimization.
17 August 2024 in International Journal of Networked and Distributed Computing
The Internet of Vehicles (IoV) enhances vehicular communication, promising better connectivity and user experiences. However, maintaining stable data delivery in dynamic vehicular environments is challenging. This paper introduces Mob-Cach, a novel mobility-aware cache management strategy that leverages real-time vehicular mobility information. Our preliminary study on LTE signal quality shows that mobility patterns significantly impact signal degradation. Based on these findings, we developed a dynamic caching framework that adapts to real-time mobility data, optimizing content delivery and network performance. Simulations demonstrate significant improvements in cache hit rates, reduced latency, and overall network efficiency. This research lays a foundation for future advancements in IoV networks, addressing the challenges of mobile and dynamic network topologies.
Swarm robotics is a particularly promising approach for autonomous exploration in complex and uncertain environments, with applications ranging from environmental monitoring to hazardous-area inspection. A major challenge lies in optimising robot trajectories to minimise travel distance while ensuring comprehensive and effective coverage of the exploration area. In this context, we propose a hybrid path-planning framework that combines the SARSA Reinforcement Learning algorithm with the ACO approach, drawing inspiration from collective coordination mechanisms in nature, particularly the use of pheromones as a medium for self-organisation. This framework leverages both individual learning and swarm intelligence in a complementary manner, thereby enabling more robust, scalable, and efficient exploration. A comparative analysis of the two methods was conducted to identify the most effective approach for optimising robot trajectories while minimising energy consumption. In this process, robots take into account obstacle avoidance, whether obstacles are traversable, using either pheromone-based environmental marking or reinforcement learning strategies. Simulation results demonstrate the effectiveness of a hybrid model that integrates SARSA with ACO, significantly enhancing trajectory quality and exploration coverage. However, they also reveal that increasing the environment size substantially increases the total travel distance and slows SARSA convergence due to the expansion of the state space. To overcome this limitation, future work will explore neural network–based value function approximation, which is expected to improve generalisation and accelerate convergence in large-scale scenarios.
With the rising worldwide need for green power sources, dependable and efficient photovoltaic (PV) systems are emerging as one of the most promising choices among sustainable energy supplies. Precise modeling of solar generators is crucial to improve their energy conversion efficiency, rendering this necessity even more critical. The precise extraction of photovoltaic (PV) model parameters is crucial for the assessment of the PV system. Many current techniques for obtaining photovoltaic parameters exhibit poor precision and are susceptible to local optima. A Circulatory System Based Optimization (CSBO) is developed to address these flaws. This research presents an innovative approach for extracting essential characteristics of the single diode model (SDM), double diode model (DDM), and three diode model (TDM) of RTC FRANCE silicon solar cells utilizing the recently discovered CSBO, which has not been previously employed in this context. A CSBO utilizes the root mean square error (RMSE) to precisely compute the current of a PV unit and is examined. Non-linear equations are employed for the accurate resolution of the I-V curve in RTC FRANCE silicon solar cells. Comprehensive simulations are performed to assess the efficacy of the suggested strategy and its efficacy relative to other metaheuristic techniques. The findings indicate that CSBO markedly decreases the Root Mean Square Error (RMSE), achieving optimal RMSE values of 9.860218 × 10− 04, 9.824848 × 10− 04,9.803370 × 10− 04, and 2.425074 × 10− 03 for SDM, DDM, TDM, and Photowatt-PWP-201 module respectively, with a smaller RT (Running Time) for all the PV cell models. The findings validate the enhanced performance and precision of CSBO which is adopts circulation-inspired search strategies to enhance the global exploration, local exploitation, population diversity, convergence speed, and premature convergence avoidance, relative to current methodologies, demonstrating that it yields more dependable parameter estimations and contributes to increased energy conversion efficiency in solar systems.