Edge computing oriented virtual optical network mapping scheme based on fragmentation prediction

As edge computing services soar,the problem of resource fragmentation situation is greatly worsened in elastic optical networks(EON).Aimed to solve this problem,this article proposes the fragmentation prediction model that makes full use of the gate recurrent unit(GRU)algorithm.Based on the fragmentation prediction model,one virtual optical network mapping scheme is presented for edge computing driven EON.With the minimum of fragmentation degree all over the whole EON,the virtual network mapping can be successively conducted.Test results show that the proposed approach can reduce blocking rate,and the supporting ability for virtual optical network services is greatly improved.

Multi-Core Virtual Concatenation Scheme Considering Inter-Core Crosstalk in Spatial Division Multiplexing Enabled Elastic Optical Networks

Spatial division multiplexing enabled elastic optical networks(SDM-EONs) are the potential implementation form of future optical transport networks, because it can curve the physical limitation of achievable transmission capacity in single-mode fiber and single-core fiber. However, spectrum fragmentation issue becomes more serious in SDM-EONs compared with simple elastic optical networks(EONs) with single mode fiber or single core fiber. In this paper, multicore virtual concatenation(MCVC) scheme is first proposed considering inter-core crosstalk to solve the spectrum fragmentation issue in SDM-EONs. Simulation results show that the proposed MCVC scheme can achieve better performance compared with the baseline scheme, i.e., single-core virtual concatenation(SCVC) scheme, in terms of blocking probability and spectrum utilization.

Cost-Minimized Virtual Elastic Optical Network Provisioning with Guaranteed QoS

Network virtualization is important for elastic optical networks(EONs)because of more flexible service provisioning.To ensure guaranteed quality of service(QoS)for each virtual elastic optical network(VEON),clients usually request network resources from a network operator based on their bandwidth requirements predicted from historical traffic demands.However,this may not be efficient as the actual traffic demands of users always fluctuate.To tackle this,we propose a new VEON service provisioning scheme,called SATP,which consists of three stages,i.e.,spectrum assignment(SA),spectrum trading(ST),and spectrum purchasing(SP).Unlike conventional once-for-all VEON service provisioning approaches,the SATP scheme first allocates spectrum resources to VEONs according to their predicted bandwidth requirements with a satisfaction ratio α(0<α≤1).Then,to minimize service degradation on VEONs which are short of assigned spectra for their peak traffic periods,the scheme allows VEONs to trade spectra with each other according to their actual bandwidth requirements.Finally,it allows VEON clients to purchase extra spectrum resources from a network operator if the spectrum resources are still insufficient.To optimize this entire process,we formulate the problem as a mixed integer linear programming(MILP)model and also develop efficient heuristic algorithms for each stage to handle large test scenarios.Simulations are conducted under different test conditions for both static and dynamic traffic demand scenarios.Results show that the proposed SATP scheme is efficient and can achieve significant performance improvement under both static and dynamic scenarios.

Reinforced virtual optical network embedding algorithm in EONs for edge computing

As the core technology of optical networks virtualization, virtual optical network embedding(VONE) enables multiple virtual network requests to share substrate elastic optical network(EON) resources simultaneously and hence has been applicated in edge computing scenarios. In this paper, we propose a reinforced virtual optical network embedding(R-VONE) algorithm based on deep reinforcement learning(DRL) to optimize network embedding policies automatically. The network resource attributes are extracted as the environment state for model training, based on which DRL agent can deduce the node embedding probability. Experimental results indicate that R-VONE presents a significant advantage with lower blocking probability and higher resource utilization.