Data center network load balancing method based on deep reinforcement learning

Abstract

The invention discloses a data center network load balancing method based on deep reinforcement learning. The method comprises the steps of: 1, building a virtual network topology structure environment; 2, constructing and initializing an Actor network Critic network target Actor network and a target Critic network; 3, inputting flow information in the network into the network constructed in the step 2 at set intervals, and carrying out DDPG training of a link weight optimization problem until an FCT ideal value of the network is reached; and maximizing the expectation of accumulated rewards by utilizing a training target of deep reinforcement learning, and finally extracting a decision tree from the DNN. The invention designs an efficient and light data center load balancing method. The decision tree is lighter, and the reasoning time is shorter, so that the controller can inform the terminal host of the updated link weight more quickly; and a depth deterministic strategy gradient algorithm is applied to a load balancing strategy of a data center network, and flow loads among multiple paths are balanced.

Description

technical field [0001] The invention belongs to the technical field of computer networks, and in particular relates to a method for realizing load balancing in a data center network. Background technique [0002] The most commonly used topology for data center networks is the multi-root tree topology. This regular topology allows multiple equal-cost paths between peers, thus providing a large amount of bisection bandwidth. When the network load is uneven, some links or paths will be congested, while the utilization rate of other links is not high, resulting in reduced network throughput and increased delay. Therefore, it is critical to design a reasonable and effective traffic scheduling strategy to improve the performance of throughput-sensitive and delay-sensitive applications. Equal-Cost Multipath Routing (ECMP) is currently the most commonly used load balancing solution in data centers. The switch locally selects the corresponding path for the flow according to the has...

AI Technical Summary

Problems solved by technology

But the routing decision made by the agent for each flow inevitably leads to a long decision delay

Because the majority of data center traffic is short flows, most flows end before their decision arrives, and the decision becomes useless

And, for better performance, DRL agents may have to use large deep neural network models with millions or even billions of parameters, which makes the situation worse the longer the decision time becomes

Images