1,720,966 research outputs found
Proposal and investigation of an ETSI NFV architecture supporting aI-based resource prediction
No full textThe high reconfiguration time of cloud resources in Network Function Virtualization architecture has led to make ineffective the reactive cloud resource allocation procedures whose application lead to over-allocate resources or to degrade Quality of Service in decreasing/increasing traffic scenario. Recently many Artificial Intelligence (AI)-based allocation procedures have been proposed to pre-allocate cloud resource according to required processing capacity predictions. In this paper we illustrate how an ETSI NFV architecture can support these predictions procedures. Furthermore they aim to exactly predict the processing capacity to be allocated and they are all based on the minimization of a symmetric loss function of the neural network. For this reason we propose a resource allocation procedure with a asymmetric loss function whose parameters are dependent on an overall cost expressed in terms of allocation and QoS degradation costs. We prove that the proposed solution allows for a cost reduction in the order of 30% in a typical NFV traffic and network scenario
Application of an Innovative Convolutional/LSTM Neural Network for Computing Resource Allocation in NFV Network Architectures
No full textAn innovative resource allocation framework for virtualized network environments and based on the application of Artificial Intelligence techniques is proposed and investigated. It integrates the needed processing capacity prediction procedure and the allocation one which determines the capacity under-allocation or over-allocation needed to minimize the resource allocation and Quality of Service degradation costs. The proposed solution is based on: i) a monitoring procedure in which the processing capacities required by virtual instances are periodically monitored; ii) an integrated allocation/prediction procedure in which the processing capacities to be allocated to the virtual instances are evaluated in time intervals successive to the monitoring periods. This second procedure uses a Convolutional/Long Short Term Memory neural network whose loss function is defined so as to minimize an overall cost dependent on both the cloud resource allocation and Quality of Service degradation costs. We evaluate the proposed solution in backbone and metropolitan traffic and network scenario. We show how in the traffic scenario of an Italian Mobile Operator in Milan zone, the proposed solution far outperforms the not integrated classical solution in which the capacity prediction and allocation procedures are separately performed. Furthermore its performance are very near to the one of an oracle that optimizes the capacity over/under dimensioning parameter
Impact of the maximum number of switching reconfigurations on the cost saving in network function virtualization environments with elastic optical interconnection
Full text linkNetwork Function Virtualization is based on the virtualization of the network functions and it is a new technology allowing for a more flexible allocation of cloud and bandwidth resources. In order to employ the flexibility of the technology and to adapt its use according to the traffic variation, reconfigurations of the cloud and bandwidth resources are needed by means of both migration of the Virtual Machines executing the network functions and reconfiguration of circuits interconnecting the Virtual Machines. The objective of the paper is to study the impact of the maximum number of switch reconfigurations on the cost saving that the Networking Function Virtualization technology allows us to achieve. The problem is studied in the case of a scenario with an elastic optical network interconnecting datacenters in which the Virtual Machines are executed. The problem can be formulated as an Integer Linear Programming one introducing a constraint on the maximum number of switch reconfigurations but due to its computational complexity we propose a low computational complexity heuristic allowing for results close to the optimization ones. The results show how the limitation on the number of possible reconfigurations has to be taken into account to evaluate the effectiveness in terms of cost saving that the Virtual Machine migrations in Network Function Virtualization environment allows us to achieve
Proposal and investigation of an optical reconfiguration cost aware policy for resource allocation in network function virtualization infrastructures
No full textThe paper proposes and investigates the problem of the reconfiguration of cloud and bandwidth resources in Multi-Provider Network Function Virtualization architectures where the Cloud Infrastructures (CI) are managed by different Providers and interconnected by an elastic optical network. The resource reconfiguration is performed by taking into account the different costs charged by the Infrastructure Providers (InP) of the CIs and by exploiting the advantages of the adaptive optical modulation. The objective is to minimize the total cost given by the sum of three components: i) the cloud resource cost; ii) the bandwidth costs; iii) the reconfiguration costs characterized by the revenue loss of the Telecommunication Service Provider due to the degradation of the Quality of Service occurring during the reconfiguration of the optical circuits. We define and investigate a heuristic of polynomial complexity. The application of the heuristic to the large distance USNET network for typical traffic and network parameters allows for a saving by 40% in total cost with respect to the case in which a traditional policy is applied
Distributed LSTM-based cloud resource allocation in network function virtualization architectures
No full textThe high reconfiguration time of cloud resources in Network Function Virtualization environments has led to the proposal of prediction-based resource allocation algorithms, with extensive use of artificial intelligence techniques. The prediction of processing capacities performed jointly and centrally has proved to be very complex due to the high communication overhead required. For this reason, we propose a distributed prediction technique in which Long Short-Term Memory neural networks exchange only a few weights in order to drastically reduce the communication overhead compared to the centralized case. We propose and investigate three different distributed solutions and show how they allow for low prediction errors
Cost-aware and aI-based resource prediction in softwarized networks
No full textResource prediction algorithms have been recently proposed in Network Function Virtualization Architectures. An prediction-based resource allocation is characterized by higher operation costs due to: i) resource underestimate that leads to Quality of Service degradation; ii) used cloud resource over allocation when a resource overestimate occurs. To reduce such a cost, we propose cost-aware prediction algorithm able to minimize the sum of the two cost components previously mentioned. We compare in a real network and traffic scenario the proposed technique to the traditional one in which the Root Mean Squared Error. We show home the proposed solution allows for cost advantages in the order of 20%
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Study and investigation of SARIMA-based traffic prediction models for the resource allocation in NFV networks with elastic optical interconnection
No full textThe paper investigates resource allocation problems in Network Function Virtualization (NFV) network architectures in which the datacenters are interconnected by an Elastic Optical Network and the offered traffic is predicted by a Seasonal Autoregressive Integrated Moving Average (SARIMA) model. We apply a procedure for deseasonalizing, eliminating the trend, estimating the parameters of the SARIMA model and forecasting real traffic values. The procedure is able to forecast the traffic so as to minimize the network operation cost and taking into account the following cost components: i) the cloud resource costs occurring when a higher resource provisioning is accomplished due to traffic overestimation; ii) the Quality of Service (QoS) degradation cost due to the user traffic loss occurring when the traffic is underestimated and fewer resources than needed are allocated
Reconfiguration of optical-NFV network architectures based on cloud resource allocation and QoS degradation cost-aware prediction techniques
Full text linkThe high time required for the deployment of cloud resources in Network Function Virtualization network architectures has led to the proposal and investigation of algorithms for predicting trafc or the necessary processing and memory resources. However, it is well known that whatever approach is taken, a prediction error is inevitable. Two types of prediction errors can occur that have a different impact on the increase in network operational costs. In case the predicted values are higher than the real ones, the resource allocation algorithms will allocate more resources than necessary with the consequent introduction of an over-provisioning cost. Conversely, when the predicted values are lower than the real values, the allocation of fewer resources will lead to a degradation of QoS and the introduction of an under-provisioning cost. When over-provisioning and under-provisioning costs are different, most of the prediction algorithms proposed in the literature are not adequate because they are based on minimizing the mean square error or symmetric cost functions. For this reason we propose and investigate a forecasting methodology in which it is introduced an asymmetric cost function capable of weighing the costs of over-provisioning and under-provisioning differently. We have applied the proposed forecasting methodology for resource allocation in a Network
Function Virtualization architectures where the Network Function Virtualization Infrastructure Point-of-Presences are interconnected by an elastic optical network.We have veried a cost savings of 40% compared to solutions that provide a minimization of the mean square error
- …
