Quantum Neural Networks for Resource Allocation in Wireless Communications
Abstract : This study exploits a quantum neural network (QNN) for resource allocation in wireless communications. A QNN is presented to reduce time complexity while still maintaining performance. Moreover, a reinforcement-learning-inspired QNN (RL-QNN) is presented to improve the performance. Quantum circuit design of the QNN is presented to ensure the practical implementation in noisy intermediate-scale quantum (NISQ) computers. For the QNN, the complexity and the number of required qubits are analyzed as well. As a particular use case, the QNN is utilized for user grouping in non-orthogonal multiple access. The results reveal that the QNN schemes have lower complexities and similar performance in terms of the achievable sum rate when compared with that of the classical neural network.
? We formulated the generic energy efficiency problem and approached it, using both classical and quantum neural network models.
? We conducted the design of the learning and training analysis for both these models to clarify their rationalism, with architectural differences and similarities.
? Such a feature is known as universal quantum computation and enables fast optimization with minimum memory demands because the number of the required qubits depends only on the width of the network at hand.
? This study is the first to consider resolving the energy efficiency problem using QNN deep learning in an effort to provide incentives for exploring the quantum perspective in different and more complex communications problems.
? These optimization problems have the structure of a learning problem in which the statistical loss appears as a constraint, motivating the development of learning methodologies to attempt their solution.
? Optimal resource allocation problems are as widespread as they are challenging.
? This permits dual domain operation in a wide class of problems and has lead to formulations that yield problems that are more tractable, although not necessarily tractable without resorting to heuristics.
? In general, wireless optimization problems do have constraints as we are invariably trying to balance capacity, power consumption, channel access, and interference.
• To identify the key parameters of the proposed QNN training process with respect to those utilized in ANN approaches, we draw our focus to a widely-adopted system modeling.
• This latter feature results in considerable memory savings and makes the proposed QNN deep-learning process highly practicable to apply in a realistic system setting and scaling.
• We extend the globally optimal power control framework of by adding a training perceptron unitary operator to test the reliability of the proposed QNN architecture.
• We proposed Algorithm 1 as the tangible mean of applying our QNN model, and conducted a series of benchmarks to evaluate its size and the number of training steps.
? In fast time varying fading channels, the system allocates resources instantaneously but users get to experience the average performance across fading channel realizations.
? A similar example in which the instantaneous performance functions are not concave is when we use a set of adaptive modulation and coding modes.
? This issue is often neglected but it can cause significant discrepancies between predicted and realized performances.
? We restrict our attention to the increasingly popular set of parameterizations known as deep neural networks (DNNs), which are often observed in practice to exhibit strong performance in function approximation.
|