With the increasing number of base stations (BSs) and network densification in 5G, interference management using link scheduling and power control are vital for better utilization of radio resources. However, the complexity of solving link scheduling and the power control problem grows exponentially with the number of BS. Due to high computation time, previous methods are useful for research purposes but impractical for real time usage. In this paper we propose to use deep neural networks (DNNs) to approximate optimal link scheduling and power control for the case with multiple small cells. A deep Q-network (DQN) estimates a suitable schedule, then a DNN allocates power for the corresponding schedule. Simulation results show that the proposed method achieves over five orders of magnitude speedup with less than nine percent performance loss, making real time usage practical.Index Terms-deep neural networks, deep reinforcement learning, scheduling, power allocation
In this paper, we propose a general framework for combining deep neural networks (DNNs) with dynamic programming to solve combinatorial optimization problems. For problems that can be broken into smaller subproblems and solved by dynamic programming, we train a set of neural networks to replace value or policy functions at each decision step. Two variants of the neural network approximated dynamic programming (NDP) methods are proposed; in the value-based NDP method, the networks learn to estimate the value of each choice at the corresponding step, while in the policy-based NDP method the DNNs only estimate the best decision at each step. The training procedure of the NDP starts from the smallest problem size and a new DNN for the next size is trained to cooperate with previous DNNs. After all the DNNs are trained, the networks are fine-tuned together to further improve overall performance. We test NDP on the linear sum assignment problem, the traveling salesman problem and the talent scheduling problem. Experimental results show that NDP can achieve considerable computation time reduction on hard problems with reasonable performance loss. In general, NDP can be applied to reducible combinatorial optimization problems for the purpose of computation time reduction.
Network traffic matrix (TM) is a critical input for capacity planning, anomaly detection and many other network management related tasks. The TMs are often computed from link load measurements. The TM estimation problem is the determination of the TM from link load measurements. The relationship between the link loads and the TM that generated the link loads can be modeled as an under-determined linear system and has multiple feasible solutions. Therefore, prior knowledge of the traffic demand pattern has to be used in order to find a potentially feasible TM. In this paper, we consider the TM estimation problem with limited prior information. Unlike previous methods that require past measurements of complete TMs, which are hard to obtain or protected by regulations, our method works even if only the distribution of TMs is known. We develop an iterative projection based algorithm to solve this problem. If large number of past TMs can be measured, we propose a Generative Adversarial Network (GAN) based approach for solving the problem. We compare the strengths of the two approaches and evaluate their performance for several networks using varying amounts of past data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.