parallel recombinative simulated annealing (PRSA) is applied to the static lightwave establishment network operation problem for wavelength division multiplexing (WDM) networks. It is assumed that the cross-connects d...
详细信息
ISBN:
(纸本)1932415068
parallel recombinative simulated annealing (PRSA) is applied to the static lightwave establishment network operation problem for wavelength division multiplexing (WDM) networks. It is assumed that the cross-connects do not perform wavelength conversion. An asynchronous version of PRSA is implemented on a multiprocessor computer with multiple interacting populations. The cooling coefficient, population size, and the number of migrants is varied for PRSA to determine the affect on the convergence rate and the quality of the final solution. It behaves like a simulated annealing (SA) algorithm, but has the advantage of being easy to implement on multiple processors.
network flow records consist of categorical and numerical features that provide context data and summary statistics computed from the raw packets exchanged between pairs of nodes in a network. Flow records labeled by ...
详细信息
ISBN:
(纸本)9783031046735;9783031046728
network flow records consist of categorical and numerical features that provide context data and summary statistics computed from the raw packets exchanged between pairs of nodes in a network. Flow records labeled by human experts are typically used in high speed networks to design and evaluate intrusion detection systems. In spite of the ever-increasing body of literature on flow-based intrusion detection, there is no contribution that investigates the accuracy of flow records at rendering the class of traffic of the original aggregation of packets. This paper proposes a collaborative filtering approach to compute sanitized labels for a given set of flow records. Sanitized labels are compared with the labels assigned by human experts. Experiments are done with CICIDS2017, i.e., an intrusion detection dataset that provides raw packets and labeled flow records obtained from benign operations and attack conditions. Results indicate that around 3.61% flow records might fail to render benign aggregations of packets;surprisingly, the percentage of flow records, which fail to render aggregations of packets pertaining to attacks, ranges from 5.39% to 27.18% depending on the type of attack. These findings indicate the need for improving the features collected or potential imperfections while computing the flow records.
Mobile edge computing (MEC) has been regarded as a promising paradigm for increasing the computing capacity of mobile devices (MDs) by offloading tasks to edge servers. Non-orthogonal multiple access (NOMA) is a criti...
详细信息
ISBN:
(数字)9781665486439
ISBN:
(纸本)9781665486439
Mobile edge computing (MEC) has been regarded as a promising paradigm for increasing the computing capacity of mobile devices (MDs) by offloading tasks to edge servers. Non-orthogonal multiple access (NOMA) is a critical multiple access technique that allows many MDs to transmit on the same resource block simultaneously. Attracted by the enormous benefits of combining NOMA and MEC, we investigate the dynamic computation offloading in a multi-device multi-server NOMA-MEC system. We consider the partial offloading policy such that MDs can offload a portion of the task to the edge server for execution. To minimize the overall computation delay and energy consumption, we formulate a mixed integer programming (MIP) problem to jointly optimize edge server selection and offloading task ratio. Solving the optimization problem with a discrete-continuous hybrid action space is not straightforward since most existing deep reinforcement learning (DRL) algorithms are only applicable to discrete or continuous action spaces. We present the hybrid advantage actor-critic (HA2C) approach, which employs an actor-critic architecture consisting of two parallel actor networks and a critic network, to tackle this problem. Specifically, the discrete actor and continuous actor networks based on deep neural networks (DNNs) determine MEC server selection and offloading ratio, respectively. The critic network evaluates the current state value, and the advantage function is computed for the discrete and continuous network parameter updates. Experimental results show that the proposed algorithm is superior to conventional DRL algorithms that convert the hybrid action space into a unified homogeneous action space.
In distributed computing, location transparency-the decoupling of objects, tasks, and virtual machines from their physical location-is desirable in that it can simplify application development and management, and enab...
详细信息
ISBN:
(纸本)9781479927289
In distributed computing, location transparency-the decoupling of objects, tasks, and virtual machines from their physical location-is desirable in that it can simplify application development and management, and enable load balancing and efficient resource allocation. Many existing systems for location transparency are built on top of TCP/IP. We argue that addressing mobile objects in terms of the host where they temporarily reside may not be the best design decision. When objects can migrate, it becomes necessary to use a dedicated routing infrastructure to deliver inter-object messages, such as location servers or forwarding chains. This incurs high costs in terms of complexity, overhead, and latency. In this paper, we defer object overlay routing to an underlying networking layer, by assuming a location independent routing scheme in place of TCP/IP. In this scheme, messages are directed to destinations determined by flat identifiers instead of IP addresses. Consequently, messages are delivered directly to a recipient object, instead of a possibly out-of-date location. We explore the scheme in the context of a small object-based language with asynchronous message passing, in the style of core Erlang. We provide a standard, network-oblivious operational semantics of this language, and a network-aware semantics which takes many aspects of distribution and message routing into account. The main result is that execution of a program on top of an abstract network of processing nodes connected by asynchronous point-to-point communication channels preserves the network-oblivious behavior in a sound and fully abstract way, in the sense of contextual equivalence. This is a novel and strong result for such a low-level model. Previous work has addressed distributed implementations only in terms of fully connected TCP underlays. But in this setting, contextual equivalence is typically too strong, due to the need for locking to resolve preemption arising from object mobility.
Digital signal processing as a key and difficult point of network technology research and development, currently commonly used content such as LabVIEW. But from a practical point of view, while these techniques can be...
详细信息
The IP packet length distribution is changing with the Internet development and traffic. Different network also has different IP packet length distribution. Now, the IP packets processing methods of many non-ATM netwo...
详细信息
ISBN:
(纸本)0780378407
The IP packet length distribution is changing with the Internet development and traffic. Different network also has different IP packet length distribution. Now, the IP packets processing methods of many non-ATM network nodes are similar with Segment and Reassemble (SAR). The payload length of the cell is fixed. When the network node is placed in a network, a large mount of redundant bytes, which result from the zero-pads and headers being used, decrease the processing bandwidth. And, when a well-designed node is placed in different network with different distribution, the processing bandwidth of the node may be even lower. In this paper, an adaptive IP packets SAR processing solution, which can adapt the traffic of the network, is present. And, the computer simulations based on the packet length statistic data are also given.
We design a new interconnection network topology and a custom routing algorithm, which targets solving new challenging issues posed by recent advanced studies in the areas of massively parallelcomputing and large-sca...
详细信息
ISBN:
(纸本)9781479913497;9781479913503
We design a new interconnection network topology and a custom routing algorithm, which targets solving new challenging issues posed by recent advanced studies in the areas of massively parallelcomputing and large-scale data centers. We follow the design principles of Distributed Shortcut networks (DSN) [1], which construct non-random topologies with the creation of long-range Shortcuts inspired by observations in small-world networks. As a result, our new DSN-alpha networks performs significantly better than the basic DSN in term of communication latency while provide an surprisingly load balance which helps the network become robust against burst of traffic demand while topology-agnostic deadlock-free routing (e.g. the up*/down*) suffers a lot.
In this paper, we propose a method to support content-based search, one of the challenges in Peer-to-Peer file sharing system. The proposed method is based on a hybrid structure, which is a combination of a Chord ring...
详细信息
In this paper, we propose a method to support content-based search, one of the challenges in Peer-to-Peer file sharing system. The proposed method is based on a hybrid structure, which is a combination of a Chord ring and a balanced tree. The tree is used to aggregate and classify terms while the Chord ring is used to index terms of nodes in the tree. At every node in the tree, the system classifies terms as either important or unimportant. Important terms of a node, which can distinguish the node from its neighbor nodes, are indexed in the Chord ring while unimportant terms that are either popular or rare terms are aggregated to higher level nodes. Based on the classification, the system can process queries on the fly without the need of global knowledge. Therefore, our system can avoid the problem of bottleneck at nodes keeping global knowledge and the expensive cost of synchronization global knowledge among these nodes. We have done extensive experiments to validate the effectiveness and efficiency of our proposal.
This paper describes several results of parallel and distributed computing using a production flow solver program. A coarse grained parallelization based on clustering of discretization grids, combined with partitioni...
详细信息
ISBN:
(纸本)3540414290
This paper describes several results of parallel and distributed computing using a production flow solver program. A coarse grained parallelization based on clustering of discretization grids, combined with partitioning of large grids, for load balancing is presented. An assessment is given of its performance on tightly-coupled distributed and distributed-shared memory platforms using large-scale scientific problems. An experiment with this solver, adapted to a Wide Area network environment, is also presented.
Efficient synchronization is one of the basic requirements of effective parallelcomputing. A key operation of the POSIX Thread standard (PThread) is barrier synchronization, where multiple threads block on a user-spe...
详细信息
暂无评论