Distributed Clustering Algorithm Research Articles

HEEL: A new clustering method to improve wireless sensor network lifetime

In wireless sensor networks, some resources such as memory and energy are limited. In recent years, there has been an increasing interest in improving network lifetime. Node energy plays an important role in the network lifetime. Along with this remarkable growth in wireless sensor networks, however, there is an increasing concern over network lifetime. The principal purpose of this study is to develop an understanding of the effects of other parameters on selecting a cluster head. The methodological approach taken in this study is a mixed methodology typically based on the node's energy. The authors have operated four parameters to select the cluster head: Node energy, the energy of the node's neighbours, number of hops and number of links to neighbours. Each of these parameters has an impact in selecting the cluster head. They accurately observed hop size, energy of each sensor node, average energy of sensor neighbours, links to sensor nodes (HEEL) has better improvements in comparison of Node ranked Low Energy Adaptive Clustering Hierarchy (Nr-LEACH), Modified Low Energy Adaptive Clustering Hierarchy (ModLEACH), Low Energy Adaptive Clustering Hierarchy-B (LEACH-B), Low Energy Adaptive Clustering Hierarchy (LEACH), Power-Efficient Gathering in Sensor Information System (PEGASIS), energy-aware clustering scheme with transmission power control for sensor networks (EACLE) and hybrid energy efficient distributed clustering (HEED) algorithms in possible case of network lifetime and throughput.

A Distributed Clustering Algorithm Guided by the Base Station to Extend the Lifetime of Wireless Sensor Networks.

Clustering algorithms are necessary in Wireless Sensor Networks to reduce the energy consumption of the overall nodes. The decision of which nodes are the cluster heads (CHs) greatly affects the network performance. The centralized clustering algorithms rely on a sink or Base Station (BS) to select the CHs. To do so, the BS requires extensive data from the nodes, which sometimes need complex hardware inside each node or a significant number of control messages. Alternatively, the nodes in distributed clustering algorithms decide about which the CHs are by exchanging information among themselves. Both centralized and distributed clustering algorithms usually alternate the nodes playing the role of the CHs to dynamically balance the energy consumption among all the nodes in the network. This paper presents a distributed approach to form the clusters dynamically, but it is occasionally supported by the Base Station. In particular, the Base Station sends three messages during the network lifetime to reconfigure the value of the network. The , which stands out as the number of rounds in which the same CHs are kept, is adapted to the network status in this way. At the beginning of each group of rounds, the nodes decide about their convenience to become a CH according to a fuzzy-logic system. As a novelty, the fuzzy controller is as a Tagaki–Sugeno–Kang model and not a Mandami-one as other previous proposals. The clustering algorithm has been tested in a wide set of scenarios, and it has been compared with other representative centralized and distributed fuzzy-logic based algorithms. The simulation results demonstrate that the proposed clustering method is able to extend the network operability.

SOFCluster: Safety‐oriented, fuzzy logic‐based clustering scheme for vehicular ad hoc networks

AbstractVehicular ad hoc network (VANET) nodes are characterized by their high mobility and by exhibiting different mobility patterns. Therefore, VANET clustering schemes are required to account for the mobility parameters among neighboring nodes to produce relatively stable clustering schemes. In this article, we propose a novel cluster‐head (CH) selection scheme for VANETs. This scheme is based on a fuzzy logic‐powered, k‐hop distributed clustering algorithm. It deals efficiently with scalability and stability issues of VANETs and is able to achieve highly stable clustering topologies as compared with other schemes. Our proposed clustering scheme strives to maintain a safe intervehicle distance as a one prime metric for CH selection. Moreover, a major contribution of our work is the proposal of a novel strategy for constructing fuzzy logic‐based clustering algorithms useful for VANETs. This proposed solution is useful in an Internet of things‐based setting that involves controlled vehicle‐to‐vehicle communication. We first derive mathematically, a new average distance estimation formula that is used as a metric for selecting CHs, leading to safer clusters that avoid collisions with front and rear vehicles. Furthermore, the new proposed scheme creates stable clusters by reducing reclustering overhead and prolonging clusters' lifetimes.

Distributed Soft Clustering Algorithm for IoT Based on Finite Time Average Consensus

Clustering is a common technique for statistical data analysis and it has been widely used in many fields. This article investigates data clustering over the Internet-of-Things (IoT) network. Facing the IoT network challenges, including data volume, communication latency, and information security, we here propose a distributed soft clustering algorithm for the IoT environments where each IoT node may have data from multiple clusters. Considering that the main task of soft clustering is to compute each cluster center in a weighted averaging fashion, our distributed clustering method resorts to an efficient finite-time average-consensus algorithm. Moreover, to make the distributed clustering algorithm more stable and be able to escape from some bad local optimum, we propose a distributed deterministic initialization method based on data variance partitioning. Experiments show that the proposed distributed soft clustering algorithm can offer the same performance as its centralized counterpart in terms of both convergence and clustering quality. Besides, unlike most clustering methods relying on probabilistic initialization, our algorithm could provide stable clustering quality which makes it more suitable for IoT networks. A real-world case study about the clustering analysis for distributed data sets collected by environmental monitoring stations is offered, which shows the potential of our algorithms in practical applications.

User online behavior based on big data distributed clustering algorithm

With the development of big data technology more and more perfect, many colleges and universities have begun to use it to analyze the construction work. In daily life, such as class, study, and entertainment, the campus network exists. The purpose of this article is to study the online behavior of users, analyze students’ use of the campus network by analyzing students, and not only have a clear understanding of the students’ online access but also feedback on the operation and maintenance of the campus network. Based on the big data, this article uses distributed clustering algorithm to study the online behavior of users. This article selects a college online user as the research object and studies and analyzes the online behavior of school users. This study found that the second-year student network usage is as high as 330,000, which is 60.98% more than the senior. In addition, the majority of student users spend most of their online time on the weekend, and the other time is not much different. The duration is concentrated within 1 h, 1–2 h, 2–3 h in these three time periods. By studying the user’s online behavior, you can understand the utilization rate of the campus network bandwidth resources and the distribution of the use of the network, to prevent students from indulging in the virtual network world, and to ensure that the network users can improve the online experience of the campus network while accessing the network resources reasonably. The research provides a reference for network administrators to adjust network bandwidth and optimize the network.

Distributed Clustering Algorithm in Sensor Networks via Normalized Information Measures

Distributed data clustering in sensor networks is receiving increasing attention with the development of network technology. A variety of algorithms for distributed data clustering have been proposed recently. However, most of these algorithms have trouble with either non-Gaussian shaped data clustering or model order selection problem. In order to address such two problems simultaneously, we propose a novel discriminative clustering algorithm with rigorous convergence analysis via normalized information measures and then extend it to a distributed one by borrowing consensus algorithms from the multi-agent consensus community. More specifically, we first select the normalized information distance (NID) between cluster data and cluster labels as the objective function, by minimizing which, a Minimum Normalized Information Distance-based (MNID) algorithm with capabilities of non-Gaussian data clustering and model selection is then proposed. Next, to further implement the MNID algorithm in a distributed manner, we employ some finite-time multi-agent consensus algorithms over the sensor networks to calculate the global model parameters, where only local intermediate variables are exchanged between one-hop neighbors. Both the centralized and the distributed MNID algorithms are proved to converge rigorously. Finally, the validity of the proposed algorithms is demonstrated through numerical tests on both synthetic and real data.

Distributed Graph Clustering and Sparsification

Graph clustering is a fundamental computational problem with a number of applications in algorithm design, machine learning, data mining, and analysis of social networks. Over the past decades, researchers have proposed a number of algorithmic design methods for graph clustering. Most of these methods, however, are based on complicated spectral techniques or convex optimisation and cannot be directly applied for clustering many networks that occur in practice, whose information is often collected on different sites. Designing a simple and distributed clustering algorithm is of great interest and has comprehensive applications for processing big datasets. In this article, we present a simple and distributed algorithm for graph clustering: For a wide class of graphs that are characterised by a strong cluster-structure, our algorithm finishes in a poly-logarithmic number of rounds and recovers a partition of the graph close to optimal. One of the main procedures behind our algorithm is a sampling scheme that, given a dense graph as input, produces a sparse subgraph that provably preserves the cluster-structure of the input. Compared with previous sparsification algorithms that require Laplacian solvers or involve combinatorial constructions, this procedure is easy to implement in a distributed setting and runs fast in practice.

EUDFC - Enhanced Unequal Distributed Type-2 Fuzzy Clustering Algorithm

Wireless sensor networks are composed of nodes that monitor the environment and send their measurements to a base station. Due to the reduced computational and energetical resources of the sensor nodes, network organization must take into account those constraints to reduce energy consumption and, in turn, to prolong the lifetime of the network. Thus, collaborative management techniques, like clustering, are usually implemented. This paper proposes a novel unequal distributed clustering algorithm for wireless sensor networks that employs a new set of input variables. Compared with previous works, these variables help for a more accurate estimation of the convenience of a node to be a cluster head. The developed algorithm relies on local information of the sensors to diminish the data exchange, reduce the interference and the consumption of the transmission processes. Because of the underlying uncertainty of the local data, a type-2 fuzzy logic system constitutes the basis of the proposed clustering algorithm whose knowledge base is sampled to allow its feasible implementation in a node. In addition, it is used an unequal scheme for the cluster sizes because it has been demonstrated that those methods are more convenient in terms of energy consumption. The simulation results demonstrate the effectiveness of the algorithm to extend the network lifetime.

DENCAST: distributed density-based clustering for multi-target regression

Recent developments in sensor networks and mobile computing led to a huge increase in data generated that need to be processed and analyzed efficiently. In this context, many distributed data mining algorithms have recently been proposed. Following this line of research, we propose the DENCAST system, a novel distributed algorithm implemented in Apache Spark, which performs density-based clustering and exploits the identified clusters to solve both single- and multi-target regression tasks (and thus, solves complex tasks such as time series prediction). Contrary to existing distributed methods, DENCAST does not require a final merging step (usually performed on a single machine) and is able to handle large-scale, high-dimensional data by taking advantage of locality sensitive hashing. Experiments show that DENCAST performs clustering more efficiently than a state-of-the-art distributed clustering algorithm, especially when the number of objects increases significantly. The quality of the extracted clusters is confirmed by the predictive capabilities of DENCAST on several datasets: It is able to significantly outperform (p-value <0.05) state-of-the-art distributed regression methods, in both single and multi-target settings.

Double Deep Autoencoder for Heterogeneous Distributed Clustering

Given the issues relating to big data and privacy-preserving challenges, distributed data mining (DDM) has received much attention recently. Here, we focus on the clustering problem of distributed environments. Several distributed clustering algorithms have been proposed to solve this problem, however, previous studies have mainly considered homogeneous data. In this paper, we develop a double deep autoencoder structure for clustering in distributed and heterogeneous datasets. Three datasets are used to demonstrate the proposed algorithms, and show their usefulness according to the consistent accuracy index.

Heed Protocol Using A Cluster Based V2V Communication

Objectives: Wireless sensor Networks employs a set a sensor nodes to monitor the parameters of the environment. The sensory information collected by the sensor nodes can be retrieved with the help of Mobile Nodes fixed upon vehicles. Existing scenarios engage both single-hop data transfer from Sensor nodes that lie within the mobile network range or profound participation of network margin nodes. These nodes are at the peril of quick energy collapse resulting in loss of network connectivity and decrease in network lifetime. The main idea behind this paper is to enhance the network lifetime and security. Methods/Statistical Analysis: The proposed HEED (Hybrid energy efficient Distributed Clustering) protocol reduces the overall network operating cost and energy disbursement associated with the multi hop data recovery process while also ensuring fair energy utilization among Sensor nodes and prolonged network lifetime. In multi hop network, the nodes closer to the sink node are involved in almost all data transmission, hence their energy would be quickly drained out. Since the energy depletion at sink node is more than other nodes, energy holes are created. Therefore other nodes in the VANET are disconnected from the network which reduces the network lifetime. To enhance network lifetime routing protocols are introduced in addition to HEED protocol which provides efficient clustering. To improve the security Intrusion-Tolerant Routing protocol (INSENS) protocol is used, which uses multipath technique in order to make the network resilient to attacks. Findings: The proposed HEED protocol elects the cluster head periodically based on a metric which is based on parameters like residual energy of the node, closeness of its neighbors and the degree of the node. The number of iterations involved in HEED protocol is very less and it achieves literally consistent distribution of cluster head allotment across the network involving a low level of information overhead. With suitable limits on node density, intra and inter cluster transmission ranges, this protocol can assure connectivity of clustered networks. Simulation results prove that this protocol is efficient in enhancing the lifetime of the network and sustaining scalable data aggregation. In case of Distributed clustering algorithms it is the responsibility of the base station to collect the information gathered by the cluster heads. In this work each and every sensor node broadcasts it accessibility to its surrounding. Based on the broadcast information the cluster head belonging to the specific cluster is identified in parallel. INSENS protocol is used to enhance network security. Simulation results prove that this protocol is efficient in enhancing the security of the network. Application/Improvements: This study proposes centralized, HEED_INSENS protocols to solve the coverage problem in VANETs. It is also useful for applications that require data aggregation and those where all data originated from sources should reach the sink without prior aggregation. Keywords: Sensor Nodes, Network Overhead, Network Lifetime, HEED, INSENS

An Energy-Conserving Collision-Free MAC Protocol for Underwater Sensor Networks

An underwater sensor network (UWSN) has recently attracted considerable attention due to its ability to discover and monitor the aquatic environment. However, its acoustic communication has posed several inherent characteristics, such as high latency, low available bandwidth, and high bit error rate. These unique characteristics have made contention-based medium access control (MAC) protocols inefficient for UWSNs. They are most expensive and are not as effective as they are in terrestrial networks. Through this principle, a contention-free MAC protocol is, therefore, considered to be more reliable and flexible to overcome the consequences of applying acoustic signals and also to achieve a high performance (improving the energy efficiency and throughput across the network) by eliminating the chance of collision. In this paper, we propose a novel energy-conserving and collision-free depth-based layering MAC (DL-MAC) protocol for UWSNs. DL-MAC is able to deal with the underwater MAC challenges, such as the near-far effect, spatial-temporal uncertainty, and hidden/exposed terminal problems. It is able to efficiently schedule the transmission and reception operations in each side by using the concept of layering and a distributed clustering algorithm. By using a TDMA-based principle, DL-MAC can assign separate time slots to every sensor node individually to access the medium without any possibility of collision. Our extensive simulation study shows that DL-MAC outperforms other protocols in terms of throughput, packet delivery ratio, energy consumption, and packets lost under varying traffic rates and the numbers of nodes.

Priority Incorporated Zone Based Distributed Clustering Algorithm for Heterogeneous Wireless Sensor Network

Priority Incorporated Zone Based Distributed Clustering Algorithm for Heterogeneous Wireless Sensor Network

An improved incomplete AP clustering algorithm based on K nearest neighbours

With the fast development of internet of things (IoT), a large amount of missing data is produced in the process of data collection and transmission. We call these data incomplete data. Many traditional methods use imputation or discarding strategy to cluster incomplete data. In this paper, we propose an improved incomplete affinity propagation (AP) clustering algorithm based on K nearest neighbours (IAPKNN). IAPKNN firstly partitions the dataset into complete and incomplete dataset, and then clusters the complete data set by AP clustering directly. Secondly, according to the similarity, IAPKNN extends the responsibility and availability matrices to the incomplete dataset. Finally, clustering algorithm is restarted based on the extended matrices. In addition, to address the clustering efficiency of large scale dataset, we give a distributed clustering algorithm scheme. Experiment results demonstrate that IAPKNN is effective in clustering incomplete data directly.

An improved incomplete AP clustering algorithm based on K nearest neighbours

With the fast development of internet of things (IoT), a large amount of missing data is produced in the process of data collection and transmission. We call these data incomplete data. Many traditional methods use imputation or discarding strategy to cluster incomplete data. In this paper, we propose an improved incomplete affinity propagation (AP) clustering algorithm based on K nearest neighbours (IAPKNN). IAPKNN firstly partitions the dataset into complete and incomplete dataset, and then clusters the complete data set by AP clustering directly. Secondly, according to the similarity, IAPKNN extends the responsibility and availability matrices to the incomplete dataset. Finally, clustering algorithm is restarted based on the extended matrices. In addition, to address the clustering efficiency of large scale dataset, we give a distributed clustering algorithm scheme. Experiment results demonstrate that IAPKNN is effective in clustering incomplete data directly.

Target Coverage-Aware Clustering in Directional Sensor Networks: A Distributed Approach

Existing clustering algorithms for directional sensor networks mainly focused on maximizing network lifetime and/or data delivery performances. A distributed clustering algorithm named TRACE considering target coverage is proposed in this paper that improves the clustering performances, as well as, the sensing coverage in the network. TRACE is designed to operate in a fully distributed manner. It is also a light-weight clustering algorithm based on coverage and connectivity, where only single-hop neighborhood information is exploited by the nodes to determine cluster heads (CHs) and two-hop neighborhood messages for gateways. Moreover, a target-coverage algorithm is proposed, where the TRACE CHs try to activate the minimum number of sensor nodes in the network, as well as, greedily maximize the number of covered targets. To measure the performances, the TRACE system is implemented in Network Simulator version 3 (NS-3) and the simulation outcomes depict that the proposed TRACE performs better than the state-of-the-art work in terms of cluster-coverage ratio, network lifetime, and overhead.

Distributed Algorithms for MaximizingLifetime in Clustered Wireless SensorNetworks Using Energy-Harvesting RelayNod

Motivated by recent developments in Wireless Sensor Networks(WSNs), we present distributed clustering algorithms for maximizingthe lifetime of WSNs, i.e., the duration till the first node dies. Westudy the joint problem of prolonging network lifetime by introducing clustering techniques and energy-harvesting (EH) nodes. Firstlywe propose distributed clustering algorithm for maximizing the lifetime of clustered WSN, which includes EH nodes, serving as relaynodes for cluster heads (CHs). Secondly graph-based and LP-basedEH-CH matching algorithms are proposed which serve as benchmarkalgorithms. Extensive simulation results show that the proposed algorithms can achieve optimal or suboptimal solutions efficiently

Rural Broadband Access via Clustered Collaborative Communication

Broadband penetration in rural areas of the developing countries is significantly low. The unique challenges in enabling rural connectivity are sparsity of population locations and modest income of the villagers, which induce low return on investment to the conventional cellular network providers. In this paper, we propose a novel cluster-based network architecture and protocols for efficient rural broadband coverage which requires minimal infrastructure setup by the service provider. Multiple customer premise equipments (CPEs) in a village form clusters and transmit collaboratively over unused television bands to the base station. A two-tier uplink access protocol is proposed and its performance in terms of network throughput and energy efficiency are obtained analytically. The cluster size is optimized to maximize the uplink network throughput and energy-efficiency. A distributed clustering algorithm is proposed for the CPEs to form clusters, while channels are allocated to the clusters using the proposed channel allocation algorithm to minimize inter-cluster interference. Via network simulation studies we demonstrate that the proposed architecture can be cost-effective and energy-efficient, while being scalable at the same time.

An efficient multi-hops clustering and data routing for WSNs based on Khalimsky shortest paths

In this paper, we propose a novel energy-efficient data routing algorithm for clustered WSNs, based on Khalimsky topology. The aim of this algorithm is to compute Khalimsky paths for optimized data routing and to provide distributed clustering algorithm reducing the energy consumption and extending the network lifetime. The clustering algorithm divides WSNs into k-hop ( $$k\geq 2$$ ) large dynamic clusters. In each cluster, nodes are arranged in concentric layers around an elected cluster-head according to well-defined criteria. Depending on its distance to the cluster-head, some nodes are selected by the triangulation theory as Khalimsky anchors to ensure optimal intra-cluster data routing. The Khalimsky anchors, located in border layers of adjacent clusters, are used for inter-cluster data routing. We prove that large clusters reduce the isolated nodes number. By this structure of multi-hops large clusters, we prove that the data routing across Khalimsky anchors alleviates the cluster heads tasks and minimizes the energy consumption. Simulation results show that our approach outperforms other protocols by achieving longer lifetime considering the energy consumption and the died nodes number.

Mind Map based Survey of Conventional and Recent Clustering Algorithms: Learning’s for Development of Parallel and Distributed Clustering Algorithms

Mind Map based Survey of Conventional and Recent Clustering Algorithms: Learning’s for Development of Parallel and Distributed Clustering Algorithms