Dynamic Network Function Instance Scaling Based on Traffic Forecasting and VNF Placement in Operator Data Centers

Tang, Hong; Zhou, Danny; Duan, Chen

doi:10.1109/tpds.2018.2867587

Cited by 85 publications

(35 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the computational complexity of the ILP problem, heuristic algorithms are used to find an approximated solution in practical applications [7], [24], [33]. Some of existing work discuss that resource and workload prediction assists in improving the operation efficiency of network [34], [35], [36].…”

Section: Literature Reviewmentioning

confidence: 99%

“…A forecast-assisted SFCs placement by affiliation-aware VNF placement is presented in [34], where the future VNF requirements can be forecasted based on fourier-series prediction method. In [35], the authors proposed a traffic forecasting method by analyzing the traffic characteristics in data center networks and implemented two VNF placement algorithms to scale the VNF instances dynamically, where the optimization problem is formulated to minimize the number of virtual machines for deploying VNFs. Deeplearning-assisted VNF orchestration in data center elastic optical network is discussed in [36].…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Service Chaining Placement Based on Satellite Mission Planning in Ground Station Networks

Gao

Liu

Kaushik

2021

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

As per the increase in satellite number and variety, satellite ground station should be required to offer user services in a flexible and efficient manner. Network function virtualization (NFV) can provide a new paradigm to allocate network resources on demand for user services over the underlying network. In this paper, we investigate the virtualized network function (VNF) placement and routing traffic problem in satellite ground station networks. We formulate the problem of resource allocation as an integer linear programming (ILP) model and the objective is to minimize the link resource utilization and the number of servers used. Considering the information about satellite orbit fixation and mission planning, we propose location-aware resource allocation (LARA) algorithms based on Greedy and IBM CPLEX 12.10, respectively. The proposed LARA algorithm can assist in deploying VNFs and routing traffic flows by predicting the running conditions of user services. We evaluate the performance of our proposed LARA algorithm in three networks of Fat-Tree, BCube and VL2. Simulation results show that our proposed LARA algorithm performs better than that without prediction, and can effectively decrease the average resource utilization of satellite ground station networks.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Service Chaining Placement Based on Satellite Mission Planning in Ground Station Networks

Gao

Liu

Kaushik

2021

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

show abstract

“…A traffic prediction-based approach is proposed in [35]- [36] in the case of NFV networks in which the NFVI-PoP are interconnected by an EON [35]- [36]; the SFC traffic parameters are predicted in [37]- [38] by applying a LSTM recurrent network. Tang [39] proposes a traffic prediction method for scaling resources in NFV environments based on traffic modeling with an Autoregressive Moving Average (ARMA); the predicted traffic values are obtained by minimizing MSE. Among the solutions based on the prediction of the resources to be allocated, Farahnakian [40] proposes regressive algorithms for estimating memory and processing consumption in cloud datacenters; the proposed solutions are based on Linear Regression [41] and K-Nearest Neighbor Regression (K-NNR) [42] methods that notoriously determine the prediction by minimizing symmetric error functions.…”

Section: Related Work and Research Motivationmentioning

confidence: 99%

Reconfiguration of Optical-NFV Network Architectures Based on Cloud Resource Allocation and QoS Degradation Cost-Aware Prediction Techniques

et al. 2020

View full text Add to dashboard Cite

The 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 traffic 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 underprovisioning 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 verified a cost savings of 40% compared to solutions that provide a minimization of the mean square error.

show abstract

“…Flow rate of each i ∈ I, f i (t) (t ∈ T ), varies over time. The state-of-theart methods [6], [28] with some advanced schemes like RNN (recurrent neural network) can comparatively predict the flow rate precisely. Since that is not the emphasis of this paper, we assume that f i (t) can be accurately predicted.…”

Section: System Model a Geo-distributed Nfv Systemmentioning

confidence: 99%

A Hybrid Learning Framework for Service Function Chaining Across Geo-Distributed Data Centers

Tang

2020

IEEE Access

View full text Add to dashboard Cite

Service function chaining (SFC) focuses mainly on deploying various network functions in geographically distributed data centers and providing interconnect routing among them. Traditional (convex optimization-based) SFC algorithms exhibit some disadvantages on the scalability and accuracy. Recently, researches have shown the effectiveness of deep reinforcement learning (DRL) in the field of SFC. However, current DRL-based algorithms possess an extremely large action space, which leads to slow convergence and poor scalability. Some researchers relieve this issue by reformulating the SFC problem, which usually results in low utilization and high cost. To address this issue, we develop a hybrid DRL-based framework which decouples the VNF deployment and flow routing into different modules. In the proposed framework, a DRL agent is only responsible for learning the policy of VNF deployment. We customize the structure of the agent base on deep deterministic policy gradient (DDPG) and adopt several techniques to improve the learning efficiency, such as adaptive parameter noise, wolpertinger policy, and prioritized experience replay. The flow routing is conducted in a game-based module (GBM). We design a decentralized routing algorithm for the GBM to address the scalability. The end-to-end latency of flows is minimized while the resource capacity and location constraints are satisfied. During the learning process of the proposed framework, the DRL agent improves its deployment policy with the reward from the GBM (the value of reward depends on flow routing). Thus, the VNF deployment and flow routing are still jointly optimized. Compared to existing DRL-learning algorithms, the proposed hybrid DRL framework can achieve a lower cost since 1) the action space is significantly reduced due to flow routing decoupling; 2) the flow routing procedure is more efficient (the GBM adopts model-based information, e.g., the gradient). Through trace-driven simulations, we show the efficiency of our algorithm compared to existing DRL-based algorithms. INDEX TERMS service function chaining; deep reinforcement learning; game theory; cloud computing

show abstract

Dynamic Network Function Instance Scaling Based on Traffic Forecasting and VNF Placement in Operator Data Centers

Cited by 85 publications

References 20 publications

Service Chaining Placement Based on Satellite Mission Planning in Ground Station Networks

Service Chaining Placement Based on Satellite Mission Planning in Ground Station Networks

Reconfiguration of Optical-NFV Network Architectures Based on Cloud Resource Allocation and QoS Degradation Cost-Aware Prediction Techniques

A Hybrid Learning Framework for Service Function Chaining Across Geo-Distributed Data Centers

Contact Info

Product

Resources

About