Optimizing Wireless Systems Using Unsupervised and Reinforced-Unsupervised Deep Learning

Abstract

Resource allocation and transceivers in wireless networks are usually designed by solving optimization problems subject to specific constraints, which can be formulated as variable or functional optimization. If the objective and constraint functions of a variable optimization problem can be derived, standard numerical algorithms can be applied for finding the optimal solution, which however incur high computational cost when the dimension of the variable is high. To reduce the online computational complexity, learning the optimal solution as a function of the environment's status by deep neural networks (DNNs) is an effective approach. DNNs can be trained under the supervision of optimal solutions, which however, is not applicable to the scenarios without models or for functional optimization where the optimal solutions are hard to obtain. If the objective and constraint functions are unavailable, reinforcement learning can be applied to find the solution of a functional optimization problem, which is however not tailored to optimization problems in wireless networks. In this article, we introduce unsupervised and reinforced-unsupervised learning frameworks for solving both variable and functional optimization problems without the supervision of the optimal solutions. When the mathematical model of the environment is completely known and the distribution of environment's status is known or unknown, we can invoke unsupervised learning algorithm. When the mathematical model of the environment is incomplete, we introduce reinforcedunsupervised learning algorithms that learn the model by interacting with the environment. Our simulation results confirm the applicability of these learning frameworks by taking a user association problem as an example.

Deep Learning Methods for Joint Optimization of Beamforming and Fronthaul Quantization in Cloud Radio Access Networks

“…where E X [•] accounts for the expectation operator over a random variable X. The equivalence between ( 6) and ( 7) is mathematically verified in [10] and the references therein. Unlike the original problem (6) which focuses on identifying the solution variables v and ω for a certain {h, P, C}, the functional optimization in (7) addresses the expected sum-rate maximization rather than its instantaneous value.…”

“…We first recast the original problem ( 6) into a functional optimization formulation [10] suitable for generalized learning for environment's status {h, P, C}. It transforms the target of the optimization into a function representing an optimization procedure.…”

Intelligent Trajectory Design for Secure Full- Duplex MIMO-UAV Relaying Against Active Eavesdroppers: A Model-Free Reinforcement Learning Approach

“…However, this assumption can be somehow impractical inasmuch as a precise mathematical model can hardly be formed, owing to the fact that the UAV-network topology frequently demands information exchange between the UAV and the core network. Consequently, the expression of the objective function to be optimized or the constraints might be either unavailable or obtaining their gradients analytically becomes almost impossible [39]. Hence, other optimization approaches are required to deal with such complex problems.…”

Unsupervised Wireless Network Model‐Assisted Abnormal Warning Information in Government Management

“…How to solve the problems and difficulties encountered in the development of township finance and maintain the stability and sustainable development of township government finance has become increasingly urgent, and the study of township finance risk has become a hot research topic in the relevant academic fields and an urgent task for the relevant functional departments [10]. Even many people still believe that if the township government has financial problems, they can only wait for the state to issue relevant policies to solve them, resulting in the financial risks at the lowest level not being given sufficient attention [11]. This thesis is based on the evaluation and prediction of township government finance in the current period from the perspective of the debt risk of township government and tries to provide useful ideas and ways to prevent and solve the financial risk of township government [12].…”