We run extensive simulations to evaluate DeepCoop, and the results show that DeepCoop can adapt to the dynamic environment in a multi-domain SD-EON to always select the best RSA heuristic for minimizing blocking probability, and it outperforms the existing algorithms on inter-domain provisioning in various scenarios.
To ensure scalability and universality, we design the action space of each DRL agent based on well-known RSA heuristics, and architect the agents based on the soft actor-critic (SAC) scenario. By sharing a restricted amount of information among each other, the DRL agents can make their decisions distributedly. DeepCoop employs a DRL agent in each domain to optimize intra-domain service provisioning, while a domain-level path computation element (PCE) is introduced to obtain the sequence of the domains to go through for each lightpath request. Specifically, we propose DeepCoop, which is an inter-domain service framework that uses multiple cooperative DRL agents to achieve scalable network automation in a multi-domain SD-EON. This motivates us to revisit the inter-domain provisioning problem in this paper by leveraging deep reinforcement learning (DRL). Therefore, even though numerous RSA heuristics have been proposed, there does not exist a universal winner that can always achieve the lowest blocking probability in all the scenarios of a multi-domain SD-EON. The service provisioning in multi-domain software-defined elastic optical networks (SD-EONs) is an interesting but difficult problem to tackle, because the basic problem of lightpath provisioning, i.e., the routing and spectrum assignment (RSA), is N P-hard, and each domain is owned and operated by a different carrier. Training of Cooperative DRL Agents 1 initialize parameters of A-NN and C-NNs for all DRL agents into D j 24 for each Domain j ∈ do 25 if there are enough training samples in D j then 26 for each training step do 27 randomly select a batch of samples 28 get losses with Eqs. Our simulation results demonstrate that DRL-Observer converges fast in online training with the help of a few asynchronous training threads, and the Deep-NFVOrch with it achieves better performance than several benchmarks, in terms of balancing the tradeoff among the overall resource utilization, the vNF-SC request blocking probability, and the number of network reconfigurations in a DCI-EON.
EON TIMER 1.6 WINDOW SMALLER THAN IT SHOULD BE HOW TO
The DRL-Observer is designed based on the advantage actor critic (A2C), which can interact with the network environment constantly through its deep neural network (DNN) and learn how to make wise decisions based on the environment's feedback. We introduce a DRL-based observer (DRL-Observer) to select the duration of each service cycle adaptively according to the network status. Specifically, Deep-NFVOrch works in service cycles, and tries to reduce the setup latency of vNF-SC by invoking request prediction and pre-deployment at the beginning of each service cycle. In this work, we tackle this problem by optimizing the design of a deep reinforcement learning (DR-L) based adaptive service framework, namely, Deep-NFVOrch.
EN 250 and FIOH.Due to the raising of cloud computing, how to realize adaptive and cost-effective virtual network function service chaining (vNF-SC) in a datacenter interconnection based on elastic optical network (DCI-EON) has become an interesting but challenging problem. Alarms, warnings and notifications.9ģ.1.1.
0 kommentar(er)
