Software Defined Network (SDN) is an emerging architecture that can overcome the challenges facing traditional networks. SDN enables administrator/operator to build a simpler and manageable network. New SDN paradigms are encouraged to deploy multiple (rather than centralized) Controllers to monitor the entire network. The Controller Placement Problem is one of the key issues in SDN that affect all its aspects including scalability, convergence time, fault tolerance, and node to Controller latency. Many researchers focus on solving this Problem by trying to optimize the location of an arbitrary number of Controllers. The related works in this area get less attention to two following important issues: i) Bidirectional end-to-end latency between the switch and its Controller instead of propagation latency and ii) finding the minimal number of Controllers, which is a prerequisite for locating them. In this paper, we propose a Set Covering Controller Placement Problem Model (SC(CPP)M) in order to find the least number of required Controllers with respect to carrier-grade latency requirement. The proposed model is carried out on a set of 124 graphs from the Internet Topology Zoo and solve them with IBM ILOG CPLEX Optimization package. Our results indicate that the number of required Controllers for high resilient network is dependent on topology and network size. Moreover, to achieve carrier-grade requirement, 86% of topologies must have more than one Controller.

Software-defined networking is a new network model proposed to solve the complexity of traditional network Problems and facilitate dynamic network operation and management. The separation of the control plane from the data plane is the main idea of software-defined networks. Controllers are the operating system of software-defined networks and are responsible for managing the entire network. It is essential to locate Controllers appropriately to have a balanced topology while guaranteeing low latency. In this work, a metaheuristic algorithm is used for Controller Placement. First, the Problem is formulated, and the network is partitioned by a clustering algorithm. Then, the seagull optimization algorithm is used to determine a suitable place for the Controller in each network partition dynamically. Simulations are performed on the standard network topology from the internet topology zoo dataset to evaluate the proposed method. Simulation results reveal that the proposed method performs well in case of delay and load balancing compared with the state-of-the-art optimization algorithms.

One of the Problems raised in software de, ned networks is to deter-mine the number and installation location of Controllers so that the cost of implemen-tation reduced and survivability of the network against link or node failure increased. Current investigation in SDN imposes full mesh topology in order to connect con-trollers. This approach while incurring a huge installation cost, dose not carefully incorporate network survivability requirements. In this paper, we improve an ex-isting integer programming approach to a novel model so as to e, ectively address user de, ned survivability requirements. Computational results reported also reveals that our models could be solved by state-of-the-art MIP solvers like CPLEX within a reasonable time limit.

Software-defined networks (SDNs) are an emerging area in computer networks, enabling efficient resource management in the network by decomposing data and control plans. In SDNs, network Controllers acting as the network operating systems, are responsible for serving application programs. Since a control plan consists of several Controllers, the Placement of network Controllers is a challenging issue in complex networks. While the literature has explored the number of Controllers and their Placement in the network, several fundamental parameters remain unexplored. Therefore, this topic remains open for more investigations. In this paper, we survey the work in the literature on Controller Placement in SDNs and introduce the research challenges in this area. Additionally, we present potential future research directions to advance this field.

Efficient distribution of service requests between fog and cloud nodes considering user mobility and fog nodes’ overload is an important issue of fog computing. This paper proposes a heuristic method for task Placement considering the mobility of users, aiming to serve a higher number of requested services and minimize their response time. This method introduces a formula to overload prediction based on the entry-exit ratio of users and the estimated time required to perform current requests that are waiting in the queue of a fog node. Then, it provides a solution to avoid the predicted overloading of fog nodes by sending all delay-tolerant requests in the overloaded fog node’s queue to the cloud to reduce the time required for servicing delay-sensitive requests and to increase their acceptance rate. In addition, to prevent requests from being rejected when the mobile user leaves the coverage area of the current fog node, the requests in the current fog node’s queue will be transferred to the destination fog node. Simulation results indicate that the proposed method is effective in avoiding the overloading of the fog nodes and outperforms the existing methods in terms of response time and acceptance rate.

Software-defined networks (SDN) have emerged as a new paradigm to overcome rigidity in traditional networks. SDN Controllers manage network switches through a centralized control plane. Strategically placing Controllers is vital for meeting performance needs. We model the NP-hard Controller Placement Problem ((CPP)) as multi-objective optimization reconciling switch-Controller latency, resilience to failures, inter-Controller coordination overhead and load balancing. A customized Non-dominated Sorting Moth Flame algorithm (NS-MF) with novel recombination and perturbation techniques is proposed to effectively approximate the Pareto-optimal set of Placements on large Problem instances. NS-MF is benchmarked on a diverse corpus of 41 topologies against the exhaustive POCO solver, assessing computational time and solution quality tradeoffs. Compared to POCO, the proposed algorithm attains over 20X speedup for the largest graphs with an average optimality gap within 0.8%. The proposed NS-MF demonstrates superior performance over state-of-the-art metaheuristics (NSGA-II and PSA) in reconciling proximity and diversity objectives when estimating Pareto-optimal fronts. Experimental results substantiate NS-MF's efficacy in effectively navigating objectives pertinent to resilient SDN design.

The body freedom flutter phenomenon is one of the aeroelastic instabilities that occurs due to the coupling of the aeroelastic bending mode of the wing with the short-period mode in the flight dynamics of the aircraft. By using the aeroservoelastic model and applying closed loop control, this phenomenon can be suppressed in the operating conditions of the aircraft and the velocity of this event can be increased. The simplest model aircraft capable of displaying this instability includes the flexible wing and the planar flight dynamics model. For this purpose, the wing structure is modeled using the Euler-Bernoulli beam and, the theory of minimum variable state is used to model unstable aerodynamics to make the conditions suitable for modeling the system in state space. In the control section, the elevator is used as the control surface and LQR theory with Kalman filter is used to body freedom flutter suppression. Finally, the effect of adding a closed loop control to increase the body freedom flutter velocity and the limitations of this work are studied.

Many real world Problems can be modelled as an optimization Problem. Evolutionary algorithms are used to solve these Problems. Ant colony algorithm is a class of evolutionary algorithms that have been inspired of some specific ants looking for food in the nature. These ants leave trail pheromone on the ground to mark good ways that can be followed by other members of the group. Ant colony optimization uses a similar mechanism to solve the optimization Problem. Usually the main difficulties of evolutionary algorithm for solving the optimization Problem are: early convergence, loss of population diversity, and placing in a local minimum. Therefore, it needs the way that preserves the variation and tries to avoid trapping in local minimum. In this paper by combining ant colony algorithm and mutation hybrid algorithms that leads to the better solution for optimization of FPGA (Field Programmable Gate Array) Placement Problem is made. They are different types of swarm intelligence algorithm. After designing the algorithm, its parameters tuning have been done by solving several Problems, and then the proposed methods have been compared with the other approaches. The results show that in most Problems, the proposed hybrid method is able to obtain better solutions and makes fewer errors.