Cloud-fog computing emerges to satisfy the low latency and high computation requirements of Internet of Things (IoTs) services. Elastic Optical Networks (EONs) are excellent substrate communication networks between fog datacenters and cloud datacenters. However, the uneven traffic of massive cloudfog services incurs many spectrum fragments, leading to high extra energy consumption. To solve this problem, we propose an Energy-efficient Deep Reinforced Traffic Grooming (EDTG) algorithm based on deep reinforcement learning. Unlike existing manually network features extracting methods, we convert the traditional network modal and the service routing path into colored network images to represent their states, and extract the features automatically by MobilenetV3 according to these images. With the extracted features, we implement an Advantage Actor-Critic (A2C) algorithm, whose actor module and critic module share an Artificial Neural Network (ANN) to get optimal grooming actions. Additionally, after repeated attempts and experiments, we set up an objective reward and punishment mechanism to evaluate the grooming actions. We conduct extensive simulations for performance evaluation, and the results have shown that EDTG can significantly reduce energy consumption compared with two well-performed traffic grooming algorithms.

No abstract

Fog computing emerges as a great candidate to mitigate the unsolved problems of cloud computing. Data migration between fog nodes and datacenters is placing huge bandwidth requirements on substrate optical networks. To increase network capacity and to improve network flexibility, broad attention has been given to flexible-grid technology. This paper addresses the issue of how to migrate substrate optical networks from the fixed-grid network era to the flexible-grid network era gradually, due to the unbearable capital expenditure and service stability. First, we model the network migration and elucidate the upgrade probability by calculating the node demands for upgrading. Then, based on the upgrade probability, three schemes are proposed to construct Potential Upgrade Nodes Group (PUNG). Besides, to maintain the traffic stability, a Migration-aware Service Provisioning (MSP) scheme is proposed based on PUNG. Numerical results illustrate that the proposed MSP scheme can effectively enhance the traffic stability compared to Non-migration-aware Service Provisioning (NSP) scheme, and the connection interrupted ratio is excessively reduced. INDEX TERMS Measurable migration, flexible optical networks, potential upgrade nodes group (PUNG), migration-aware service provisioning (MSP) scheme.

No abstract

No abstract