Software-Defined Network (SDN) enables a centralized networking architecture that employs controllers to administer a global view of the network. However, the architecture of SDN and OpenFlow are susceptible to scalab...
详细信息
Software-Defined Network (SDN) enables a centralized networking architecture that employs controllers to administer a global view of the network. However, the architecture of SDN and OpenFlow are susceptible to scalability and reliability issues. In fact, the problem of determining the requisite number of controllers and their locations in SDNs while maximizing the fault tolerance, i.e., controller Placement Problem (CPP), is NP-hard. Besides, the communication latency between the forwarding nodes and the controllers are usually very high in large-scale SDNs due to sparse deployment. This paper first formulates the CPP as Nonlinear Programming (NLP). Then, we present an efficient greedy heuristic method that employs a local Optimized High Degree and Independent Dominating Set (OHDIDS) strategy to address these issues. In particular, we examine the CPP based on Silhouette analysis, Gap Statistics, and Faster Partitioning Around Medoids (FPAM) techniques. We conduct extensive experiments using Internet Topology Zoo and Mininet network simulators to show the efficacy of the proposed method with various network topologies. The proposed method outperforms the state-of-the-art methods in terms of the minimum number of controllers, average-case and worst-case latency, and reliability. We observed that our method reduces the average communication latency by 57% when two controllers are used rather than a single controller. Moreover, it achieves a performance gain of up to 19.31% in terms of average propagation latency.
In this paper the problem of synchronisation of multiple robotic manipulators using Hoo robust distributed control systems with respect to the parameter uncertainties and disturbance inputs acting on the manipulators ...
详细信息
In this paper the problem of synchronisation of multiple robotic manipulators using Hoo robust distributed control systems with respect to the parameter uncertainties and disturbance inputs acting on the manipulators is addressed. Robust synchronising controllers only use the information of outputs of the manipulators, and the corresponding parameters of these output-feedback controllers are designed by computing a series of linear matrix inequalities instead of solving the complex differential (e.g. Hamilton-Jacobi) (in)equalities. The proposed controller can guarantee H ∞ robust performance with respect to the external disturbance inputs and parameters uncertainties, asymptotic stability and synchronisation in the networked manipulators. Using an illustrative example we compare the results extracted in this paper to other works existing in the literature.
The main advantage of software defined network (SDN) is a separation of data and control planes to facilitate network management functions. This separation nevertheless poses a scalability and availability problem for...
详细信息
ISBN:
(纸本)9781538691861
The main advantage of software defined network (SDN) is a separation of data and control planes to facilitate network management functions. This separation nevertheless poses a scalability and availability problem for controllers in the control plane. controllers become a single point of failure in SDN. This paper presents an approach of a hybrid controller network for improving scalability and availability in both local and global domains. This approach extends controller architecture to providing direct communication among controllers in the global domain. It applies a peer-to-peer (P2P) protocol for controllers to facilitate group formation and data synchronization. We have extended the prototyping implementation of the Gnutella protocol to evaluate the performance of the hybrid controller network and to simulate controller failure and switch migration. The experimental results show that controllers perform large data update efficiently with low extra workload as number of controllers increase significantly.
Software defined network (SDN) is a new architecture for network in which the control plane is separated from data plane and implemented centrally. There are two general models for the control plane, single and distri...
详细信息
ISBN:
(纸本)9781728108728
Software defined network (SDN) is a new architecture for network in which the control plane is separated from data plane and implemented centrally. There are two general models for the control plane, single and distributed controller. A single SDN controller faces with some problems such as scalability and single point of failure. distributed model is introduced to solve these problems. The classical hierarchical model is known as one of the main kinds of distributed SDN controllers. In this paper, we introduce an efficient hierarchical SDN model to reduce the load of the root controllers in comparison with classical hierarchical model.
The modular multilevel cascaded converter (MMCC) has in recent years drawn interest for applying in the utility-scale photovoltaic (PV) and the battery energy storage (BES) systems. However, the large numbers of the c...
详细信息
The modular multilevel cascaded converter (MMCC) has in recent years drawn interest for applying in the utility-scale photovoltaic (PV) and the battery energy storage (BES) systems. However, the large numbers of the cascaded modules lead to the difficulty of the implementation with a centralized control architecture. The paper [1] has proposed a distributed control strategy which significantly reduces the complexity and increases the flexibility to expand the system. This paper continues the research which analyzes the operation range of each module and its fault tolerant capability. The analysis provides a guideline to design the MMCC controller based on the distributed control approach. Simulation and experimental results are carried out on a star-connected cascaded converter to validate the analysis.
Software-defined networks(SDN) maintain a global view of the network, thus improving the intelligence of forwarding decisions. With the expansion of the network scale, distributed controllers are used in a variety of ...
详细信息
Software-defined networks(SDN) maintain a global view of the network, thus improving the intelligence of forwarding decisions. With the expansion of the network scale, distributed controllers are used in a variety of large-scale networks in which subnetworks managed by controller instance are called autonomous domains. We analyze statistic frequency of communication across the autonomous domain. We calculate the autonomous domain correlations for controller instances using acquired statistical information. We cache network views to highly correlated controller instances. distributed controllers are capable of considering both the average response time and overall storage. An experiment shows that our method can fully take advantage of these two performance indicators.
Software defined networking offers a capability of separating control plane from data plane. The control plane is the key component of a network which ensures smooth management and operation of the entire network. How...
详细信息
ISBN:
(纸本)9781509025763
Software defined networking offers a capability of separating control plane from data plane. The control plane is the key component of a network which ensures smooth management and operation of the entire network. However, network's resiliency and availability offered by SDN single centralized controller architecture is prone to single point of failure. Network operators are rather looking at distributed controllers' deployment to ensure better network resiliency and availability. This paper gives a brief overview of approaches available for distributed controller deployment and also highlights some of the challenges experienced in the SDN distributed controller environments.
Software-Defined Networking (SDN), which is relatively a new concept, proposes a more intelligent way to manage network resources. The controller is a key component in SDN, which sends management and forwarding polici...
详细信息
ISBN:
(纸本)9781509002436
Software-Defined Networking (SDN), which is relatively a new concept, proposes a more intelligent way to manage network resources. The controller is a key component in SDN, which sends management and forwarding policies to switches by flow entries. With the increase of network scale, there are too many flows to install, especially in data center (DC). The number of flow entries is up to 757,000. This has exceeded the processing capability of centralized controller. Thus we put forward a distributed architecture to install flows. There are two ways to install flow entries, proactive and reactive. In proactive way, flows are stored in the distributed storage in a key-value way, and use the identifier of switch as the key of flows. As for reactive way, one controller instance sends flow entries to other controller instances other than the synchronize function of distributed storage. We build a prototype system on Floodlight to demonstrate our design and test the performance of our solution. According to the experiment, our design to install flows has a good scalability and better performance. In the reactive mode, it can save 10 times of time than the synchronize way.
This paper presents a robust nonlinear distributed controller design for islanded operation of microgrids in order to maintain active and reactive power balance. In this paper, microgrids are considered as inverter-do...
详细信息
This paper presents a robust nonlinear distributed controller design for islanded operation of microgrids in order to maintain active and reactive power balance. In this paper, microgrids are considered as inverter-dominated networks integrated with renewable energy sources (RESs) and battery energy storage systems (BESSs), where solar photovoltaic generators act as RESs and plug-in hybrid electric vehicles as BESSs to supply power into the grid. The proposed controller is designed by using partial feedback linearization and the robustness of this control scheme is ensured by considering structured uncertainties within the RESs and BESSs. An approach for modeling the uncertainties through the satisfaction of matching conditions is also provided in this paper. The proposed distributed control scheme requires information from local and neighboring generators to communicate with each other and the communication among RESs, BESSs, and control centers is developed by using the concept of the graph theory. Finally, the performance of the proposed robust controller is demonstrated on a test microgrid and simulation results indicate the superiority of the proposed scheme under different operating conditions as compared to a linear-quadratic-regulator-based controller.
This paper presents a nonlinear distributed controller design for islanded operation of microgrids in order to maintain active and reactive power balance. In this paper, the microgrids are considered as inverter-domin...
详细信息
ISBN:
(纸本)9781479964154
This paper presents a nonlinear distributed controller design for islanded operation of microgrids in order to maintain active and reactive power balance. In this paper, the microgrids are considered as inverter-dominated networks integrated with renewable energy sources (RESs) and battery energy storage systems (BESSs) where solar photovoltaic (PV) generators act as RESs and plug-in hybrid electric vehicles (PHEVs) as BESSs to supply power into the grid. The detail dynamic models of PV generators and BESSs are also developed in this paper. The proposed distributed control scheme gathers information from local and neighboring generators to achieve the desired control objectives. The proposed controller is designed by using feedback linearization and the communication between generators and control centers is developed by using the concept of graph theory. Finally the performance of the proposed controller is demonstrated on a test microgrid and simulation results indicate the superiority under different operating conditions as compared to a linear quadratic regulator (LQR)-based controller.
暂无评论