Integrated Deep Temporal Learning and Reinforcement Optimization for Energy-Efficient Routing and Clustering in Wireless Sensor Networks

In recent years, energy-efficient data collection has evolved into the core problem in the resource-constrained Wireless Sensor Networks (WSNs). Different from existing data collection models in WSNs, we propose a collaborative data collection scheme based on optimal clustering to collect the sensed data in an energy-efficient and load-balanced manner. After dividing the data collection process into the intra-cluster data collection step and the inter-cluster data collection step, we model the optimal clustering problem as a separable convex optimization problem and solve it to obtain the analytical solutions of the optimal clustering size and the optimal data transmission radius. Then, we design a Cluster Heads (CHs)-linking algorithm based on the pseudo Hilbert curve to build a CH chain with the goal of collecting the compressed sensed data among CHs in an accumulative way. Furthermore, we also design a distributed cluster-constructing algorithm to construct the clusters around the virtual CHs in a distributed manner. The experimental results show that the proposed method not only reduces the total energy consumption and prolongs the network lifetime, but also effectively balances the distribution of energy consumption among CHs. By comparing it o the existing compression-based and non-compression-based data collection schemes, the average reductions of energy consumption are 17.9% and 67.9%, respectively. Furthermore, the average network lifetime extends no less than 20-times under the same comparison.

Wireless sensor networks (WSN) play a key role in enabling wireless communication technology among several nodes to remotely communicate and exchange information. WSN consists of tiny sensor nodes equipped with battery, scattered in an area to gather information around an environment and send to data collection node known as sink or base station (BS). WSN have been widely used in various applications like agriculture, fire detection, health care and military and has become imperative necessity for future revolutionary area like UAV (unmanned aerial vehicles), IoT (Internet of things) and smart cities which employs large scale sensor nodes. However sensor nodes are limited to battery, memory, low computational power, resource and bandwidth. Continues sensing of events, makes node to drain its battery faster and goes dead fast. For resource constrained WSN, hierarchical cluster based approaches are considered as energy efficient and improves network performance for large scale WSN. Minimizing energy consumption and extending network lifetime are major challenging issues of WSN, clustering methods with optimized routing have offered solution to optimize energy utilization. To balance energy consumption and improve network lifetime many existing hierarchical clustering approaches have been proposed, however existing method does not consider rotation of cluster head (CH) and considers cluster head selection based on residual energy and distance parameter. In this paper we propose an improved energy efficient cluster tree (IEECT) based routing to improve energy efficiency of hierarchical cluster. IEECT considers modification of existing LEACH (Low energy adaptive clustering hierarchy) protocol to improved energy efficient LEACH by considering energy parameters like residual node energy and average network energy. IEECT accounts optimal number of cluster head (CH) and selection of CH is done using threshold value among sensor nodes. Proposed IEECT combines tree based routing and data aggregation scheme to maintain desirable quality of service. Simulation experiments are carried out by using network simulator. Performance of IEECT is evaluated in terms of PDR, delay, energy consumption, network lifetime and overhead.

Wireless Sensor Networks (WSNs) are essential in fields such as agriculture, education, industry, and environmental monitoring. However, given their limited energy supplies and occasional maintenance, creating energy-efficient network topologies and routing methods is a considerable problem. This work presents an approach to enhance the longevity of networks in WSN. This approach employs advanced fuzzy C-means clustering, modified particle swarm optimization (MPSO) for cluster head selection, and routingbased adaptive zebra optimization (AZO). The adaptive zebra optimization approach relies on efficient routing paths chosen for every relay nodes to send data to the base station (BS). The proposed method illustrates that the relay node facilitates and optimizes communication between the sink and the cluster head, thereby enhancing energy efficiency. Ultimately, the quality of service (QoS) in WSNs improves, enabling the system to sustain long performance. The suggested technique demonstrated superior performance compared to prior methods for energy consumption, throughput, node viability, end-to-end latency (E2E), and packet delivery ratio (PDR).

Recent developments in wireless sensor networks (WSNs) have led to significant advances in energy-efficient routing protocols through the integration of deep learning and bio-inspired optimization algorithms. WSNs face critical challenges due to limited battery capacity, computational constraints, and dynamic network topology. This review article provides a comprehensive comparative analysis of state-of-the-art approaches for energy optimization in WSNs, focusing on clustering and routing protocols. We examine three major publications that propose hybrid frameworks combining deep learning architectures (CapsNet, ResNet-50) with metaheuristic optimization algorithms (ETSA, SOPSO, ACO). The analysis categorizes these protocols based on network architecture, energy models, optimization strategies, and performance metrics. We compare their effectiveness in extending network lifetime, reducing energy consumption, improving packet delivery ratio, and minimizing transmission delay. The comparative study demonstrates that hybrid deep learning-swarm intelligence approaches achieve 18-38% improvement in network lifetime, <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{1 2} \boldsymbol{-} \mathbf{1 4 \%}$</tex> reduction in energy consumption, and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{1 5} \boldsymbol{-} \mathbf{2 4 \%}$</tex> lower delay compared to traditional protocols. This article serves as a comprehensive reference for researchers and practitioners working on nextgeneration energy-efficient WSN deployments.

Large scale Wireless Sensor Networks (WSNs) often utilize multiple mobile sink nodes to improve the network lifetime and scalability. However, most of the studies conducted in this context, consider unlimited buffer capacity for the sink nodes. But, this model cannot truly describe the behavior of WSNs and causes congestion in the sink nodes. To solve this problem, in this paper, we use limited buffer capacity for each mobile sink node in WSNs and present a two-level Fuzzy Logic Controller (FLC)-based dynamic clustering scheme and congestion prevention. In this scheme, sink nodes try to predict current load based on their loads in previous rounds by using ARIMA method and based on it, the first FLC selects the nearest uncongested sink node from multiple available mobile sink nodes. Then, the second FLC applies the output of the first FLC to select appropriate nodes as cluster heads to mitigate the energy consumption in the network. Extensive simulation results indicate the effectiveness of the proposed fuzzy logic-based solution in reducing congestion in the mobile sink nodes and improving load balancing in them which these result in the network lifetime improvement and decreasing the number of retransmissions.

In Wireless Sensor Network (WSN), the nodes have limitations in terms of energy-constraint, unreliable links, and frequent topology change. In this paper we propose an energy-aware routing protocol, that outperforms the existing ones with an enhanced network lifetime and more reliable data delivery. Major issues in the design of a routing strategy in wireless sensor networks are to make efficient use of energy and to increase reliability in data delivery. The proposed approach reduces both energy consumption and communication-bandwidth requirements and prolongs the lifetime of the wireless sensor network. Using both analysis and extensive simulations, we show that the proposed dynamic routing helps achieve the desired system performance under dynamically changing network conditions. The proposed algorithm is compared with one of the best existing routing algorithms, GRAB. Moreover, a modification in GRAB is proposed which not only improves its performance but also prolongs its lifetime.

Wireless Sensor Networks are vital for applications like environmental monitoring, smart cities, and industrial Internet of Things, yet their efficiency is often limited by sensor node energy constraints. To address this, we propose a novel hybrid routing algorithm namely, Fuzzy C-Means - Fuzzy-Based Spotted Hyena Optimization - Quantum Annealing, which enhances energy efficiency and network longevity. The three-phase approach begins with adaptive fuzzy clustering, allowing nodes to belong to multiple clusters for improved load balancing. Next, the Fuzzy-Based Spotted Hyena Optimization algorithm selects initial routes using parameters such as residual energy, distance to the base station, and link quality. Finally, Quantum Annealing refines routing paths to ensure global optimization and avoid local optima. This hybrid method adapts dynamically to changing network conditions and energy levels, delivering superior scalability and performance. Experimental results show a 30% reduction in total energy consumption and a 25% increase in effective data transmission. The algorithm achieves a packet delivery ratio of 98.87%, throughput of 65 kbps, and latency of 115 ms, outperforming conventional techniques. This work contributes a robust and adaptive routing solution, supporting sustainable and efficient WSN deployments in dynamic environments.

Energy efficiency is critical in Wireless Sensor Networks (WSNs), pivotal for Internet of Things (IoT) applications like environmental monitoring and smart cities. Clustering protocols like Low-Energy Adaptive Clustering Hierarchy (LEACH) extend network lifetime through Cluster Head (CH) rotation, but random CH selection often leads to suboptimal energy use. This study evaluates eight hybrid Particle Swarm Optimization-based LEACH (PSO-LEACH) variants to optimize CH selection and clustering: FA-PSO-LEACH (Firefly Algorithm), CSA-PSO-LEACH (Crow Search Algorithm), PSO-LEACH with CBTEERA, Adaptive PSO-LEACH, ABC-PSO-LEACH (Artificial Bee Colony), ACO-PSO-LEACH (Ant Colony Optimization), WOA-PSO-LEACH (Whale Optimization Algorithm), and Hybrid GA-PSO-LEACH (Genetic Algorithm). The primary research objective is to compare these variants in terms of energy efficiency, network lifetime, and clustering quality to identify the most effective strategies for prolonging WSN operation in IoT environments. Specifically, this paper addresses the research question: Which hybrid PSO-LEACH variant provides the optimal balance between early-stage stability and long-term energy conservation in a simulated WSN with 50 nodes? Each variant uses a unique metaheuristic for CH selection based on residual energy and distance, with PSO refining clustering. A Python simulation modelled a 100m × 100m WSN with 50 nodes, assessing network lifetime (First Node Died, FND; Half Nodes Died, HND; Last Node Died, LND), energy consumption, and clustering quality. Results show ABC-PSO-LEACH leading with FND at 57 rounds and LND at 462 rounds, followed by WOA-PSO-LEACH (HND 148, LND 406), surpassing others (e.g., PSO-LEACH with CBTEERA: FND 10, LND 280). WOA-PSO-LEACH’s balanced energy distribution excels in mid-to-late stages, despite computational overhead. These bio-inspired hybrids outperform traditional LEACH, with ABC-PSO-LEACH and WOA-PSO-LEACH ideal for prolonged WSN operation. Future work aims to enhance early-stage performance and explore dynamic topologies.

&lt;span&gt;The wireless sensor networks (WSNs) believed to be as a hot research area due to their ranges in various fields of applications. Clustering is the more efficient techniques considered to resolve the problems of energy consumption in WSNs. The clustering has assured its effectiveness, specifically with high dynamic networks at which all nodes are represented in the clustering and all the data value can be collecting by sensor nodes with a cluster head (CH). The energy consumption as well as network traffic are balancing, the (CH) must be exchanged between all sensor nodes and the clustering size could be closely determined at various portions of the network. The key point at issue in WSN is to improve the energy-efficient algorithms with Grid based clustering for extending the lifetime of the networks, reducing cost, in addition to increasing the reliability of the network. The sensor nodes prepared with a power sources at limited period, so that the Grid Based Clustering algorithm (GBC) which efficiently employing sensor nodes energy have the ability to preserve an extended network lifetime. Sensor node Performances of the network mainly depend on the routing protocols, which are application based, four routing protocols LEACH, OLSR, AODV, and DSR in clustering WSN are estimated with Qualnet simulator. The results demonstrate that DSR outperforms in term of throughput, and end to end delay which compared to others while OLSR have highest value of half number of alive nodes per round.&lt;/span&gt;

Clustering in wireless sensor networks has been one of the most effective mechanisms for addressing the issues of network lifetime, scalability and bandwidth reusability. In this paper, application of a relatively new meta-heuristic called as quantum inspired genetic algorithm has been proposed for dealing with the problem of multi-hop energy balanced unequal clustering and prolonging the network lifetime. Quantum inspired genetic algorithm conflates the concepts of evolutionary computation with the principles of quantum computing. The quantum computing principles impart huge parallel processing capabilities to the genetic algorithm due to which these algorithms provide better quality solutions in lesser amount of time. Quantum inspired algorithms are capable of providing competitive solutions even with a very small population size which results in reduced computational cost as population size is a factor in complexity calculation for evolutionary and swarm algorithms. The effectiveness of proposed approach has been evaluated by comparing it with traditional genetic algorithm based clustering for wireless sensor networks. Simulation results clearly indicate that quantum inspired genetic algorithm is capable of performing clustering in more efficient way and increasing the network lifetime as compared to traditional genetic algorithm.

In WSN, sensors near the sink have to relay the data of the nodes away from the sink and as a result they drain their energy very quickly. It result in network partitioning and can significantly limit the network lifetime. This problem is termed as hotspot problem. Recently, formation of hot spot or energy hole near the sink has emerged as a critical issue for data gathering in WSN. In this paper, we address hotspot problem and purposed Mobile Sink based Routing Protocol (MSRP) for Prolonging Network Lifetime in Clustered Wireless Sensor Network. In MSRP, mobile sink moves in the clustered WSN to collect sensed data from the CHs within its vicinity. During data gathering mobile sink also maintains information about the residual energy of the CHs. Mobile sink based on the residual energy of CHs move to the CHs having higher energy. Consequently, the hotspot problem is minimized as the immediate neighbor of the sink is high energy node and it changes because of regular sink movement. It results in a balanced use of WSN energy and improves network life time. To evaluate the performance of the proposed strategy intensive simulation are carried out using OMNet-4.0. Performance of the proposed strategy is compared to the static sink and multiple sinks strategies, using metrics such as energy per packet, and throughput. The simulation results demonstrate that MSRP is effective in prolonging the network lifetime as well as in improving throughput than static sink and multiple sink strategies.

Ensuring stability and extending network lifetime in Wireless Sensor Networks (WSNs) achieved through significantly reduced energy consumption is considered as a potential challenge. The selection of Cluster Head (CH) during the process of clustering is determined to be highly complicated in spite of its role in facilitating efficient and balanced energy consumption in the network. In this paper, Hybrid Stochastic Ranking and Opposite Differential Evolution enhanced Firefly Algorithm (HSRODE-FFA)-based clustering protocol is proposed for handling the issues of location-based CH selection approaches that select duplicate nodes with increased computation and poor selection accuracy. This HSRODE-FFA clustering scheme includes the process of sampling for selecting the CHs from among the sensor nodes that exist in the sample population and address the problems introduced by different locations of nodes and CHs. It is proposed as an attempt to improve stability and lifetime of WSNs based on the merits of Stochastic Firefly Ranking (SFR) that enhances the exploration capability of Firefly Algorithm (FFA). The hybridization of the enhanced FFA with Opposition Differential Evolution (ODE) aids in speeding and ensuring optimal exploitation in the selection of CHs. The proposed HSRODE-FFA thereby maintains a balance between the rate of exploitation and exploration for deriving mutual benefit of rapid and potential selection of CHs from the sampling population. The experimental results of the proposed HSRODE-FFA scheme confirm an enhanced stability period and network lifetime of 16.21% and 13.86% respectively in contrast to the benchmarked Harmony Search and Firefly Algorithm-based Cluster Head Selection (HSFFA-CHS), Krill Herd Optimization and Genetic Algorithm-based Cluster Head Selection (KHOGA-CHS), Particle Swarm Optimization with Energy Centers Searching-based Cluster Head Selection (PSO-ECS-CHS) and Spider Monkey Optimization-based Cluster Head Selection (SMO-CHS) schemes.

Improved metaheuristic based energy-efficient clustering protocol for wireless sensor networks

Recent trend to steer Wireless Sensor Networks towards a broad outdoor environment allows to monitor harsh areas and prevent a disaster situation. To guarantee an extensive work of the system and smooth cooperation among involved devices a new clustering approach needs to be found. In this paper, we present a new algorithm for an Event-oriented Focal Weight-based clustering for Wireless Sensor Network which will be able to monitor various parameters (physical, biological, and chemical) of the outdoor environment and signal the current situation further to the network. Shown results demonstrate the applicability of the algorithm for the large amount of nodes with various power levels. The use of a dual-band transceiver and advanced processing elements allow to accommodate new features in the nodes and guarantee a high performance with the low power consumption which is crucial for the outdoor system with no human attendance.

Energy utilization in a wireless sensor network (WSN) is a major concern. In WSN we cannot use rechargeable batteries, because sensor nodes are mostly deployed in areas which are not easily accessible. In this paper, we consider a one dimensional (1-D) network and look at reducing energy during routing of packets. To increase the network lifetime of a WSN, routing protocol should not unnecessarily use all the nodes in the network, instead use minimum number of nodes. So relay node selection plays an important role in energy reduction. In this paper, we use two major algorithms: energy saving via opportunistic routing algorithm (ENS_OR) and geographic random forwarding algorithm (GeRaF) for reducing energy consumption and along with these, we implement sleep mode. We show that use of sleep mode improves network lifetime by reducing energy consumption.