Unsupervised Learning-Inspired Power Control Methods for Energy-Efficient Wireless Networks Over Fading Channels

Energy-efficiency (EE) is a critical metric within wireless optimization. Power control over fading channels is considered as a promising EE-improving technique, but requires optimization of a series of fractional functional optimization problems which are hard to handle by existing optimization techniques. In this paper, we propose a novel EE power control method with unsupervised learning. Firstly, the original fractional problems are decomposed into sub-problems by Dinkelbach and quadratic transformations. Then, these sub-problems are reformulated into unconstrained forms through Lagrange dual formulation. Furthermore, unsupervised primal-dual learning method is applied to handle these unconstrained problems with strong duality. Finally, The unsupervised primal-dual learning is implemented by the deep neural network (DNN) with low computational complexity. Simulation results verify the effectiveness of the proposed approach on a number of typical wireless optimizing scenarios. It is shown that compared to conventional algorithms our method achieves better performance in cognitive radio networks, interference networks, and OFDM networks.

Automated summary

In this paper, a novel energy-efficient power control method with unsupervised learning is proposed. The method decomposes the original fractional optimization problems into sub-problems and reformulates them into unconstrained forms using Lagrange dual formulation. Unsupervised primal-dual learning, implemented by a deep neural network, is then used to handle these unconstrained problems. Simulation results show the effectiveness of the proposed approach in typical wireless optimization scenarios, achieving better performance compared to conventional algorithms.