Improving the Reliability of Software-Defined Networks with Distributed Controllers Through Leader Election Algorithm and Colored Petri-Net

Wireless Personal Communications - Software-Defined Networks (SDNs) are developed to compensate the complicated function of the controlling parts of the given network elements and making the...     

Improving the reliability of Byzantine fault‐tolerant distributed software‐defined networks

This paper presents a method to improve the reliability and fault tolerance of distributed software‐defined networks. This method is called “BIRDSDN (Byzantine‐Resilient Improved Reliable Distributed Software‐Defined Networks).” In BIRDSDN, a group communication is implemented among the controllers of the whole clusters. This method can detect the crash failure and Byzantine failure of any controller and undertakes a fast detection and recovery scheme to select the controllers to take over the orphan switches. BIRDSDN takes into account the reliability of the nodes considering the failure probability of intracluster and intercluster links, topology, load, and latency. The numerical results show that this approach performs better than the other approaches regarding failure detection, recovery, latency, throughput, reliability, and packet loss.     

Quality enhancement of video on demand implementation in peer-to-peer networks by optimum chunk length in the BitTorrent

BitTorrent in efficiency content distribution is a major concern efficiency among the researchers of this field with respect to streaming video on demand (VoD) production. BitTorrent is not appropriate for real-time applications; therefore, in order to apply it in VoD it should go through the necessary changes. Most of the available studies have greatly focused on changes in methods regarding chunk and peer selections method regarding BitTorrent, which proposed methods have improved the quality of VoD to a certain degree, while, the effect of chunk size on quality of video has been of less concern among them. Noting the fact that the buffer is used on VoD, the specified time for filling the buffer would allow for appropriate management of the chunk’s length. The Bit error rate and the time overhead of the operating algorithm parameters, somehow effect the chunk size. Because of bit error rate, the probability of correctly received chunks with great length is much less, that is, offering shorter pieces, while these pieces would lead to formation of more pieces in a buffer. The results indicate that a specific amount of time is required for obtaining the buffer’s content, and it must be dividable into more chunks. Running algorithms for each chunk generate a greater overhead which would result in of the QoS reduction. This overhead would make the bigger pieces perform better. As for the opposite impacts of these two parameters on the chunk size, in this article the optimal length of the chunks is found by considering both the effective characteristic. This optimal length is an established balance between the correctly received chunks’ rate and the greater rate of the buffer context obtained in a specified time.     

A system for providing load‐aware virtual network service in a software‐defined data center network

Virtual networks may be used in a cloud data center to provide personalized networking services for the applications running in the cloud. As the virtual networks come to the data center and leave it, the data center network load may become unbalanced where some parts of the data center has accommodated many virtual networks while a few virtual networks are mapped to other parts of the data center. This situation may lead to packet loss and service level agreement violations in an oversubscribed data center. This unbalanced state of the load in data center can be resolved by migration of virtual networks from overloaded parts of the data center to places where the load is in a lower level. This paper presents implementation details of the prototype of a system that provides virtual networking service in a cloud data center and focuses primarily on virtual network migration as a means for controlling the state of load in data center. Experimental results show that the system has an acceptable performance in reducing the packet loss ratio and keeping the load in a balanced state.     

Improving energy efficiency in information‐centric mobile ad‐hoc networks using places of interest while respecting privacy

The fact that network users mostly look for content regardless of its location has led to the creation of information‐centric networks with NDN (named data networking project) as the most famous instance. NDN can be implemented in any type of network including MANET (mobile ad‐hoc network) which can be easily created among a collection of smartphones. The first step for content retrieval in NDN is propagating interest packets which has a dramatic effect on energy consumption because of wireless communications. Methods have been devised for limiting the amount of packet propagation. But they are not appropriate for smartphones either because they require multiple WiFi interfaces which is not available in usual smartphones or because they require the exact position of nodes which conflicts privacy. In our proposed approach, a single WiFi interface is used, and mobile nodes will share only an imprecise version of their current and their predicted next location, which complies much better with privacy. Using this information, the amount of interest and data packets will decrease of more than 15%. When location information is spread through the network, this reduction will be almost doubled.     

Improving the reliability of wireless data communication in Smart Grid NAN

The communication network of a Smart Grid has a three-level hierarchical structure consisting of Home Area Network (HAN), Neighborhood Area Network (NAN) and Wide Area Network (WAN). Wireless communication, due to its advantages, is identified as a potential candidate for Smart Grid communications, especially in HAN and NAN. However, wireless transmission is inherently unreliable, whereas communication reliability is one of the fundamental requirements of Smart Grid applications. In this paper, a two-layer communication model based on IEEE reference grids is considered for NAN and a method based on transmission redundancy is proposed to improve the reliability of wireless communications in NAN, while the communication delay requirement of the Smart Grid is considered as a restriction. The proposed method finds the optimum number of transmissions at each hop with respect to the loss probability and total delay constraints. Comparing the proposed method to the case of an equal number of transmissions for all the hops, it is shown by analysis that the proposed method achieves a superior reliability while meeting the delay requirement. In addition, the simulation-based evaluation of the proposed method supports the validity of the results obtained from the analytical model.     

Applying ant colony optimization for load balancing on grid

Grid computing is comprised of many distributed nodes in order to compute and analyze a set of distributed data. To improve the processing performance, an appropriate load-balancing algorithm is required to equally distribute loads among the grid’s nodes. In this article, an algorithm based on ant colony optimization is proposed to deal with load-balancing problems. In this approach, when an ant reaches a node, the ant’s table and the node’s table exchange their information and update each other. In order to move to the most appropriate node, the ant selects the next node from the current node’s table according to the nodes’ loads and their CPU rates. This process is continued until the ant passes the predefined steps. The experimental results show that while implementing the proposed algorithm to the grid environment, increasing the number of jobs and their length has insignificant impact on the system response time.     

A novel collaborative approach for location prediction in mobile networks

Human location prediction has been a matter of concern for several years due to its many applications. It has become more important nowadays because of prevalence of mobile devices which have adequate tools for inferring location. Different approaches for making this prediction could be divided into three categories, based on the movement history they use. These include history of mobile user himself, history of all mobile users in a place, and history of only related mobile users. Besides the problem of limiting shared data to only required data, preserving privacy is the matter of concern for persuading mobile users to share their data. In this paper we have proposed a new method in which the amount of the shared data is decreased to a minimum, and only the data which will improve the partner’s prediction will be shared. Our method preserves privacy by blurring the shared data up to different degrees. The experimental results show that regardless of amount of blurring, as long as the user movement is not lost because of blurring, the accuracy of prediction will be improved about 7 %.     

Congestion avoidance by dynamically cache placement method in named data networking

The Journal of Supercomputing - In recent years, a new paradigm of Content-Centric Networks has emerged, which employs the prefix content name for addressing in the context of Named Data Networking...     

OASM: An overload‐aware workload scheduling method for cloud computing based on biogeographical optimization

With the daily increase in the number of cloud users and the volume of submitted workloads, load balancing (LB) over clouds followed by a reduction in users' response time is emerging as a vital issue. To successfully address the LB problem, we have optimized workload distribution among virtual machines (VMs). This approach consists of two parts: Firstly, a meta‐heuristic method based on biogeographical optimization for workload dispatching among VMs is introduced; secondly, we propose an innovative heuristic algorithm inspired by the “Banker algorithm” that runs in core scheduler to control and avoid VM overloads. The combination of these two (meta‐)heuristic algorithms constitutes an LB approach through which we have been able to reduce the value of the makespan to a reasonable time frame. Moreover, an information base repository (IBR) is introduced to maintain the online processing status of physical machines (PMs) and VMs. In our approach, data stored in IBR are retrieved when needed. This approach is compared with well‐known (non‐)evolutionary approaches, such as round‐robin, max‐min, MGGS, and TBSLB‐PSO. Experimental results reveal that our proposed approach outperforms its counterparts in a heterogeneous environment when the resources are smaller than the workloads. Moreover, the utilization of physical resources gradually increases. Therefore, optimal workload scheduling, as well as the lack of overload occurrence, results in a reduction in makespan.