Search

Summary: Nowadays data center networks (DCNs) should handle the ever‐growing load generated by diverse applications. It particularly occurs under concurrent flow requests and so‐called mice flows (MFs): elephant flows (EFs) ratio. Concentrating on a binary vision over flow size classification (EF or MF) results in subsequent unpredicted load imbalance due to neglecting EF's distinctions including a wide range of sizes. As a result, some EFs might utilize a path owing qualities beyond the given EF's demands, while another EF with higher requirements is attending to use an over‐utilized path. This article proposes FMap, a fuzzy map for scheduling EFs through our proposed variant of traveling salesperson problem (TSP) toward DCNs. FMap represents a novel EF scheduling scheme that integrates flow prioritization and routing decisions under the event pf parallel incoming flows besides the cooperation of the controller and OpenFlow switches in software‐defined networking (SDN) paradigm. FMap adopts fuzzy inference process to overcome the vagueness over EF's resource allocation. Mainly, FMap proposes a new variant of TSP (optimized by genetic algorithm) which enables EF's group forwarding with a minimum cost. FMap reduces the total hop count of EFs through considering a single optimal path for delivering groups of EFs that contain a same tag (priority). The outstanding results represent a major improvement as compared with equal cost multiple path, Hedera, Sonoum, and Size‐KP‐PSO. Particularly, the results illustrate an outperforming by 3.76×, 0.21×, 0.15×, 0.03×, and 0.03× in terms of total hop count, EFs FCT, packet loss, goodput, and received packets as compared with Size‐KP‐PSO, respectively. [ABSTRACT FROM AUTHOR]

The most important challenge in wireless sensor networks is to extend the network lifetime, which is directly related to the energy consumption. Clustering is one of the well-known energy-saving solutions in WSNs. To put this in perspective, the most studies repeated cluster head selection methods for clustering in each round, which increases the number of sent and received messages. what's more, inappropriate cluster head selection and unbalanced clusters have increased energy dissipation. To create balanced clusters and reduce energy consumption, we used a centralized network and relay nodes, respectively. Besides, we applied a metaheuristic algorithm to select the optimal cluster heads because classical methods are easily trapped in local minimum. In this paper, the Grey Wolf Optimizer(GWO), which is a simple and flexible algorithm that is capable of balancing the two phases of exploration and exploitation is used. To prolong the network lifetime and reduce energy consumption in cluster head nodes, we proposed a centralized multiple clustering based on GWO that uses both energy and distance in cluster head selection. This research is compared with classical and metaheuristic algorithms in three scenarios based on the criteria of "Network Lifetime", "Number of dead nodes in each round" and "Total Remaining Energy(TRE) in the cluster head and relay nodes. The simulation results show that our research performs better than other methods. In addition, to analyze the scalability, it has been evaluated in terms of "number of nodes", "network dimensions" and "BS location". Regarding to the results, by rising 2 and 5 times of these conditions, the network performance is increased by 1.5 and 2 times, respectively. [ABSTRACT FROM AUTHOR]

Anomaly is an important and influential element in Wireless Sensor Networks that affects the integrity of data. On account of the fact that these networks cannot be supervised, this paper, therefore, deals with the problem of anomaly detection. First, the three features of temperature, humidity, and voltage are extracted from the network traffic. Then, network data are clustered using the density-based spatial clustering of applications with noise (DBSCAN) algorithm. It also analyzes the accuracy of DBSCAN algorithm input data with the help of density-based detection techniques. This algorithm detects the points in regions with low density as anomaly. By using normal data, it trains support vector machine. And, finally, it removes anomalies from network data. The proposed algorithm is evaluated by the standard and general data set of Intel Berkeley Research lab (IRLB). In this paper, we could obliterate DBSCAN's problem in selecting input parameters by benefiting from coefficient correlation. The advantage of the proposed algorithm over previous ones is in using soft computing methods, simple implementation, and improving detection accuracy through simultaneous analysis of those three features. [ABSTRACT FROM AUTHOR]