Sandeep Kumar Sunori, Shilpa Jain, Pradeep Juneja et al. · 2024
This research study intends to optimize the wireless sensor nodes to minimize energy consumption for improving lifespan and performance of wireless networks. To align to this objective, Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) are used as optimization techniques in MATLAB, so that data is communicated to base stations with minimum energy consumption. Optimization needs fitness function which is based on energy consumption for sensor nodes and data transmission rates, moreover distance between the node and base station is also essential. With this ideology, it is conceptualized that sensor nodes are based on energy consumption, data transmission rates and distance from base station. PSO and GA algorithms inspect 12 sensor nodes network; position of node, energy level and data rate were different. Results obtained from both the optimization techniques are compared on basis of energy consumption and convergence rate.
Cited by 0
Bhavana Srinivas, Nadig Vijayendra Uma Reddy · IAES International Journal of Artificial Intelligence · 2025
The increasing complexity of heterogeneous wireless networks (HWNs) and the diverse requirements of mobility patterns and service classes necessitate advanced solutions for network selection and resource optimization. Existing models often fall short in addressing dynamic mobility scenarios and service differentiation, leading to inefficiencies in resource allocation, suboptimal throughput, and increased latency. To overcome these limitations, this study proposes a dynamic service-aware network selector (DSANS) framework for 5G-advanced environments. The framework integrates an adaptive deep decision network (ADDN) for multi-objective optimization, addressing critical quality of service (QoS) metrics such as throughput, delay, and energy efficiency while enhancing quality of experience (QoE) for applications like enhanced mobile broadband (eMBB), ultra-reliable low latency communication (URLLC), and internet of things (IoT). The DSANS framework dynamically adapts to mobility patterns and varying network conditions, ensuring efficient resource estimation and optimal network selection. Simulation results highlight its superiority, achieving up to 25% improvement in throughput and a 15% reduction in latency compared to state-of-the-art algorithms. These findings validate DSANS as a robust solution for mitigating the limitations of existing models, optimizing network performance, and meeting the stringent demands of next-generation HWNs.
Cited by 0Open access
Kumar R., Nirmal, R. S., Valarmathi, M., Kalamani · Tehnicki vjesnik - Technical Gazette · 2025
Wireless sensor networks (WSNs) are becoming more valuable in environmental monitoring and industrial automation.Many WSN applications need highperformance adders and multipliers for efficient computation.Due to power efficiency, latency reduction, and resource use, optimum designs are required.The Optimized Multiplier Architecture for Wireless Sensor Networks (OMA-WSN) proposed in this paper addresses these issues.WSN mathematical procedures and significance are the subject of this study.WSNs with efficient multipliers and adders are crucial.WSNs cannot use current multiplier designs because of their sluggish operation and high power consumption.OMA-WSN combines RTSBA, Booth Multiplier, and Binary Common Sub-Expression Elimination (BCS2E) algorithms for a new viewpoint.This system's architecture implements efficient computation methods that minimize logic levels and propagation delays.The cutting-edge technique improves power consumption, latency, and resource usage for WSN applications.Numerous simulations demonstrate that the OMA-WSN performs better.The performance of the proposed OMA-WSN was found to be enhanced in various aspects.Specifically, the delay was reduced to 7.56 ns in simulation and 6.32 ns in hardware.The area utilization improved to 98.56 sq.micrometres in simulation and 90.23 sq. in hardware.The power consumption was lowered to 9.87 mW in simulation and 7.56 mW in hardware.The speed increased to 160.43 MHz in simulation and 145.67 MHz in hardware.The energy efficiency was enhanced to 0.98 pJ/bit in simulation and 0.87 pJ/bit in hardware.Lastly, the adder cell utilization improved to 47.43% in simulation and 40.67% in hardware.
Cited by 0Open access
Israa Al Barazanchi, Wahidah Hashim, Reema Thabit et al. · Khwarizmia. · 2024
Wireless Body Area Networks (WBANs) are crucial in continuous health monitoring, fitness tracking, and other applications where a real-time collection of physiological data is needed by sensors worn on the body. This is important in WBAN to achieve reliable data transmission, energy efficiency, and overall system performance. Still WBANs present several challenges: for example, the data that is being collected is heterogeneous since it originates from diverse IMDs measuring different bio-physiological signals; these can be also quite noisy because of motion artifacts when moving; as well high limitations when it comes to energy, bandwidth or storage push for low-complexity methods rather than standard deep learning techniques. Common Convolutional Neural Networks) CNNs( are successfully utilized for spatial information extraction but they cannot catch temporal dependencies well and also, WBAN sensor data has a noisy and multi-modal structure which acts as an additional challenge for traditional CNNs. These limitations emphasize the need of a flexible, fast and precise classification model based on the specific needs of WBAN applications. To overcome these challenges, this paper presents a novel hybrid neural network architecture consisting of combined 2D and 3D convolutions for spatial-temporal feature extraction along with masked convolution layers to provide an ability to adaptively ignore uninterested parts of the data. The model aims at achieving a high classification performance while also balancing with the system computational efficiency, perfect for its ipsi deployment on resource constrained WBAN devices. Then, we apply further backpropagation optimization measures such as adaptive learning rate scheduling and gradient clipping, to improve the stability of training speed and reduce latency which in return finds its way into supporting real-time processing capabilities of the model. By using each of these components, the model is able to deal with the multi-dimension aspects and high noise level nature of WBANs without excessive computation resources [18]. The Hybrid Masked CNN model is shown to out-perform existing approaches without such masking, yielding substantially higher performance in terms of accuracy, precision, recall and F1-score across all metrics defined for the application as compared to traditional 2DCNNs, 3DCNNs and other hybrid models. Consequently, the latency of the model is significantly decreased as well which confirms its applicability to real-time WBAN applications. The obtained results confirm the efficacy of features from hybrid architectures with masked convolutions along with optimization in training techniques for WBAN sensor node classification. The results of this paper improve WBAN technology by providing a solid and scalable solution which can be implemented when more reliability and flexibility are required from such systems in applications like healthcare, fitness or any other field.
Cited by 9Open access
Andrea Goldsmith, Stephen Boyd, H. Vincent Poor et al. · 2012
Abstract : This document summarizes the research performed under AFOSR contract FA9550-08-1-0480, entitled Complex network information exchange in random wireless environments.'' The objective of this project was to develop novel techniques, structures, and algorithms for optimization of complex wireless networks where channels change dynamically and randomly, effecting network performance and reliability. These random dynamics, while challenging for ensuring robust high-performance network operation, also create opportunities that adaptive network control policies can exploit. This is particularly important for advanced military networks operating in rapidly changing, heterogeneous and sometimes hostile environments. A main focus of this research was to develop the new technique of Wireless Network Utility Maximization (WNUM), extending NUM ideas to include network and traffic dynamics. The research also explore optimization of network security protocols that exploit random wireless environments. Finally, compressed sensing and matrix completion ideas were explored to develop low-complexity network control.
Cited by 0
Christina Lim, Chathurika Ranaweera, Ampalavanapillai Nirmalathas et al. · 2022
In this paper, we review the work we have carried out in the investigation of the transport network in a hybrid fiber-wireless system to cater for the next generation wireless networks. We have demonstrated advanced coordination functionality in the physical layer to enable coordination between remote radio heads. We have also devised an optimization framework to jointly optimize the wireless and optical network that minimizes the deployment cost. We conclude the paper by providing insights into a reconfigurable optical architecture that can be used to support wireless networks of 6G and beyond.
Cited by 4
Yanhong Ge, Shubin Wang, Jinyu Ma · EURASIP Journal on Wireless Communications and Networking · 2018
In order to improve the energy efficiency of cognitive wireless sensor network, this paper introduces threshold-sensitive energy efficient sensor network (TEEN) routing protocol into cognitive wireless sensor network. To make routing and spectrum more stable, this paper presents advanced threshold-sensitive energy efficient sensor network (A-TEEN), which is the optimization of TEEN. A-TEEN optimized the cluster head election method compared with TEEN. Simulation result shows that compared with low-energy adaptive clustering hierarchy, TEEN increases the energy efficiency and extends life cycle of cognitive wireless sensor network. A-TEEN improves the energy efficiency and lifetime further operating in the same settings compared with the regular TEEN.
Cited by 48Open access
Jie Zheng, Ruichen Zhang, Dusit Niyato et al. · ArXiv.org · 2026
Enhancing future wireless networks presents a significant challenge for networking systems due to diverse user demands and the emergence of 6G technology. While reinforcement learning (RL) is a powerful framework, it often encounters difficulties with high-dimensional state spaces and complex environments, leading to substantial computational demands, distributed intelligence, and potentially inconsistent outcomes. Large language models (LLMs), with their extensive pretrained knowledge and advanced reasoning capabilities, offer promising tools to enhance RL in optimizing 6G wireless networks. We explore RL models augmented by LLMs, emphasizing their roles and the potential benefits of their synergy in wireless network optimization. We then examine LLM-enabled RL across various protocol layers: physical, data link, network, transport, and application layers. Additionally, we propose an LLM-assisted state representation and semantic extraction to enhance the multi-agent reinforcement learning (MARL) framework. This approach is applied to service migration and request routing, as well as topology graph generation in unmanned aerial vehicle (UAV)-satellite networks. Through case studies, we demonstrate that our framework effectively performs optimization of wireless network. Finally, we outline prospective research directions for LLM-enabled RL in wireless network optimization.
Cited by 0Open access
Jie Zheng, Ruichen Zhang, Dusit Niyato et al. · arXiv (Cornell University) · 2026
Enhancing future wireless networks presents a significant challenge for networking systems due to diverse user demands and the emergence of 6G technology. While reinforcement learning (RL) is a powerful framework, it often encounters difficulties with high-dimensional state spaces and complex environments, leading to substantial computational demands, distributed intelligence, and potentially inconsistent outcomes. Large language models (LLMs), with their extensive pretrained knowledge and advanced reasoning capabilities, offer promising tools to enhance RL in optimizing 6G wireless networks. We explore RL models augmented by LLMs, emphasizing their roles and the potential benefits of their synergy in wireless network optimization. We then examine LLM-enabled RL across various protocol layers: physical, data link, network, transport, and application layers. Additionally, we propose an LLM-assisted state representation and semantic extraction to enhance the multi-agent reinforcement learning (MARL) framework. This approach is applied to service migration and request routing, as well as topology graph generation in unmanned aerial vehicle (UAV)-satellite networks. Through case studies, we demonstrate that our framework effectively performs optimization of wireless network. Finally, we outline prospective research directions for LLM-enabled RL in wireless network optimization.
Cited by 0Open access
Jie Zheng, Ruichen Zhang, Dusit Niyato et al. · IEEE Communications Magazine · 2026
Enhancing future wireless networks presents a significant challenge for networking systems due to diverse user demands and the emergence of 6G technology. While reinforcement learning (RL) is a powerful framework, it often encounters difficulties with high-dimensional state spaces and complex environments, leading to substantial computational demands, distributed intelligence, and potentially inconsistent outcomes. Large language models (LLMs), with their extensive pretrained knowledge and advanced reasoning capabilities, offer promising tools to enhance RL in optimizing 6G wireless networks. We explore RL models augmented by LLMs, emphasizing their roles and the potential benefits of their synergy in wireless network optimization. We then examine LLM-enabled RL across various protocol layers: physical, data link, network, transport, and application layers. Additionally, we propose an LLM-assisted state representation and semantic extraction to enhance the multi-agent reinforcement learning (MARL) framework. This approach is applied to service migration and request routing, as well as topology graph generation in unmanned aerial vehicle (UAV)-satellite networks. Through case studies, we demonstrate that our framework effectively performs optimization of wireless network. Finally, we outline prospective research directions for LLM-enabled RL in wireless network optimization.
Cited by 0
Sugumar, Venkatesh, Karuppiah, Devi, Govindasamy, Kumaresan et al. · Figshare · 2025
Over the past few years, the application of Wireless Sensor Networks has rapidly increased in the healthcare sector due to their ability to continuously monitor crucial health metrics, including heart rate, blood pressure, and temperature. Traditional approaches have faced challenges in achieving fault tolerance, energy efficiency, and optimal data transmission in healthcare wireless sensor networks. To solve this challenges, this study aims to develop an advanced optimization framework. The proposed framework introduces a novel Golden Sine SeaHorse Optimization Boosted Quantum Dirichlet Convolutional Learning model. Golden Sine Optimization, SeaHorse Optimization, and Quantum Dirichlet Convolutional Learning are the advanced optimization techniques incorporated through this proposed framework to address network failures, improve energy efficiency, and optimize data delivery. Golden Sine Optimization and Quantum Dirichlet Convolutional Learning algorithms select the most economical and energy-efficient routes to optimize the exploration and exploitation balance of alternate paths. Network topology and communication paths are dynamically modified through the Quantum Dirichlet Convolutional Learning model. The proposed model achieved a packet delivery ratio of 96%, with an energy consumption of 119 millijoule and a fault recovery time of 45 milliseconds. The proposed framework exhibits significant potential for optimizing healthcare-based wireless sensor networks and fault-tolerant healthcare monitoring systems.
Cited by 0Open access
Sugumar, Venkatesh, Karuppiah, Devi, Govindasamy, Kumaresan et al. · Figshare · 2025
Over the past few years, the application of Wireless Sensor Networks has rapidly increased in the healthcare sector due to their ability to continuously monitor crucial health metrics, including heart rate, blood pressure, and temperature. Traditional approaches have faced challenges in achieving fault tolerance, energy efficiency, and optimal data transmission in healthcare wireless sensor networks. To solve this challenges, this study aims to develop an advanced optimization framework. The proposed framework introduces a novel Golden Sine SeaHorse Optimization Boosted Quantum Dirichlet Convolutional Learning model. Golden Sine Optimization, SeaHorse Optimization, and Quantum Dirichlet Convolutional Learning are the advanced optimization techniques incorporated through this proposed framework to address network failures, improve energy efficiency, and optimize data delivery. Golden Sine Optimization and Quantum Dirichlet Convolutional Learning algorithms select the most economical and energy-efficient routes to optimize the exploration and exploitation balance of alternate paths. Network topology and communication paths are dynamically modified through the Quantum Dirichlet Convolutional Learning model. The proposed model achieved a packet delivery ratio of 96%, with an energy consumption of 119 millijoule and a fault recovery time of 45 milliseconds. The proposed framework exhibits significant potential for optimizing healthcare-based wireless sensor networks and fault-tolerant healthcare monitoring systems.
Cited by 0Open access
Kripalakshmi Thiagarajan, T. Deepa, Mohan Lal Kolhe · Wireless Power Transfer · 2024
This paper introduces a new approach to boost the efficiency of wireless power transfer (WPT) for electric vehicles (EVs), through advanced coil design optimization and control techniques. Current EV charging methods struggle with slow charging times and limited adaptability. The present approach tackles these issues by optimizing electromagnetic coupling and resonance conditions, leading to improvements in both efficiency and system reliability. The proposed method includes a novel optimization algorithm, the Taylor-based Firefly and Dove Swarm Optimization (F-DSO), to fine-tune coil parameters, alongside a Bessel Filter-enhanced Fuzzy Recurrent Neural Network (FRNN) controller. The F-DSO algorithm adjusts dynamically to enhance coupling and mutual inductance, over an air gap of 135 mm. The FRNN controller maintains stable, accurate battery charging with minimal signal interference. Experimental validation shows the system achieves a peak efficiency of 95%, a state-of-charge (SOC) of 45%, and a steady battery voltage of 25 V. This approach surpasses previous configurations, such as the H-Shape DST, QDQ, and square coil setups. Additionally, the integrated LCC and series-series compensation circuits ensure reliable voltage control and stability under varying loads. These findings set a new standard for WPT, showcasing the potential of the F-DSO algorithm for broader use in the EV sector, offering more efficient, adaptable, and user-friendly charging solutions.
Cited by 3Open access
Anurag Thantharate · 2022
Title from PDF of title page, viewed January 31, 2023
Cited by 0
S Vijayalakshmi, Savita Savita · 2024
Nowadays, due to the creation of an intelligent environment, there is a rapid development of real-time applications of wireless sensor network (WSN) technology. Because of the ease of maintenance and installation of untethered wireless channels, wireless access technology is becoming more common. Wireless network design is difficult because of the highly versatile environmental conditions, which make parameter optimization a difficult job. Advanced wireless networking requirements rely increasingly on machine learning and artificial intelligence techniques due to dynamic and often unfamiliar operating environments. Genetic Algorithms (GAs) are a well-known approach to implementing AI tasks like categorization, learning and optimization. GAs are desirable for their exceptional generalization and versatility, and they’ve been used in a wide range of wireless network settings. A GA is a metaheuristic optimization computational tool for biologically inspired evolution that focuses to mimic the robust system used among different biological organisms to make adjustments during natural progression. GAs have proven to be effective in a variety of fields, including aircraft manufacturing, chip construction, computer animation, drug development, information technology, software development and economic markets. In this chapter, we discuss the role of GA in the WSN. Many problems are solved using GAs that model a short form of genetic procedures.
Cited by 0
Wenwu Yu, Xiaokai Nie, Yujin Cai et al. · Scientia Sinica Informationis · 2024
As a new generation of intelligent comprehensive digital information infrastructure, the 6th generation mobile communication (6G) deeply integrates the technologies of artificial intelligence, big data and advanced computing to build a new network mode of ubiquitous interconnection and efficient interworking of agents, which has a larger system capacity, faster information transmission rate and more intelligent and digital performance characteristics. Reconfigurable intelligent surface (RIS) is an emerging technology with great potential to drive the performance of future 6G communication networks to achieve super wireless bandwidth, hyperscale connectivity, and extremely reliable communication capabilities. This technology is based on a large number of low-cost passive reflection elements integrated on the digital metamaterial plane, and significantly improves the performance of wireless communication networks in complex scenarios through adaptive configuration of wireless propagation environments. The key to realizing adaptive dynamic regulation of communication links lies in the optimization of RIS-assisted network systems. Therefore, this paper provides a review of the relevant research literature on RIS-related network performance optimization in recent years, which summarizes the current research achievements and progress of RIS-assisted wireless communication network performance optimization from two aspects of RIS-assisted communication network architecture with performance optimization scheme, and application scenarios. This paper further discusses the potential future research directions of deployment of RIS-assisted communication networks.
Cited by 0Open access
S. M. Riazul Islam · Academica Global Journal of Computer Science and Technology Studies · 2023
The rapid growth of wireless communication networks, fueled by the increasing demand for high-speed, reliable, and scalable services, has necessitated the integration of advanced technologies to optimize network performance. Artificial Intelligence (AI) has emerged as a transformative force in this domain, offering innovative solutions for network optimization and enhancing the overall performance of wireless communication systems. This paper explores the role of AI in wireless communication, particularly focusing on its application in network traffic management, dynamic resource allocation, signal processing, and predictive maintenance. AI techniques such as machine learning, deep learning, and reinforcement learning are applied to optimize network parameters, predict failures, and enhance user experience through intelligent decision-making. Moreover, the paper discusses the integration of AI with 5G and beyond, showcasing how AI can revolutionize network architecture by enabling real-time decision-making and adaptive network management. By leveraging AI, wireless networks can achieve higher throughput, lower latency, improved coverage, and greater energy efficiency. The paper also addresses the challenges and limitations of AI integration, including data privacy concerns, computational complexity, and the need for standardization in AI-based solutions. Overall, AI-enhanced wireless communication systems offer significant advancements in network optimization and performance, making them indispensable for the future of global connectivity.
Cited by 0Open access
Lu, Feng · SMARTech Repository (Georgia Institute of Technology) · 2019
An enhanced fiber-wireless integrated system is designed using advanced system design and digital signal processing (DSP) techniques. The capacity and reliability are improved with reduced latency in the converged network. For the optical section, the peak-to-average power ratio is reduced using advanced DSP and the network architecture is optimized with novel light sources in analog links. In addition, the adaptive parameter tunning is designed for digital link enhancement. All these schemes provide enhanced capacity and reliability with higher efficiency. For millimeter-wave fiber-wireless convergence, advanced waveforms including orthogonal chirp division multiplexing, generalized frequency division multiplexing and power-division non-orthogonal multiple access are proposed and implemented, to support applications emphasizing capacity, reliability or device density. With verifications using a millimeter-wave fiber-wireless converged setup, these waveforms demonstrate better performance in various channel conditions. Finally, for the all-spectrum fiber-wireless system, the converged fiber, millimeter-wave, free-space optics and visible light communication system is designed aiming to enhance the network capacity, density and reliability by utilizing extra spectral resources. The novel system design and DSP techniques presented in the dissertation provide a reference for future wireless system standardization and network implementation. Further waveform design for all-spectrum system and machine learning based optimization are discussed for future research.
Cited by 0
Rashel, Masud R., Mesbahi, Oumaima, Ahmed, Md Tofael et al. · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) · 2021
With the advancement of technology the internet technology is evolving and it is facing new challenges to the betterment of the quality of service. Mesh Networks are an important topology where the fixed wireless network is established to provide network services. Wireless Mesh Network (WMN) is getting acknowledgment for advanced networking purposes. Mainly performance of this kind of network is dependent on the assignment of the channel and the scheme of routing. The photovoltaic network is a new concept that is combined with the Internet of Things to take advantage of the panel’s monitoring system. Large-scale WMN, combined with a photovoltaic system requires optimization techniques to improve the quality and efficiency of service. Covering and sharing information between all nodes in the network is crucial for PV and the Internet of Things (IoT). Power consumption is a significant part of low-power WMN and IoT. This article provides different optimization techniques and analyzes different algorithms to understand the better solution for a wireless mesh network in the ground of photovoltaic networking.
Cited by 1Open access
J. C. Blake · American Journal Of Sensor Networks And Wireless Communications · 2024
Wireless Sensor Networks (WSNs) have emerged as pivotal technologies in healthcare applications, enabling continuous patient monitoring, real-time health data acquisition, and efficient medical management. The deployment of advanced topologies in WSNs facilitates better energy consumption, increased network lifetime, and enhanced data transmission efficiency, critical for health monitoring systems. This paper explores the advanced topologies employed in wireless sensor networks for healthcare, with an emphasis on topology optimization, routing protocols, and system performance. The integration of WSNs in healthcare not only contributes to reducing healthcare costs but also promotes proactive healthcare management.
Cited by 0Open access