It is envisioned that 6G, unlike its predecessor 5G, will depart from connected machines and connected people to connected intelligence. The main goal of 6G networks is to support massive connectivity for time-sensitive and computation-sensitive services in mission-critical applications. The creation of real-time optimization (RTO) enabled by the fast growing data analytic and machine learning will seize the opportunities for 6G wireless networks to support such immersive services such as virtual reality (VR), augmented reality (AR), mixed reality (MR), and tactile Internet. Recently, with the rapid development of quantum computers, quantum-inspired optimization and machine learning algorithms have been exploited as efficient solutions for future wireless networks. In this article, we provide a comprehensive view on the new concept of quantum-inspired RTO and its application to the optimal resource allocation for 6G wireless networks. Our main contributions are to introduce some of the initial research results and introduce the potentiality of quantum-inspired RTO on some 6G emerging technologies. Not only do we review the fundamental principles; we also explore the challenges and opportunities of this exciting research direction.

The advent of underwater acoustic sensor networks (UASNs) has enhanced marine environmental monitoring, auxiliary navigation, and marine military defense. One of the core functions of UASNs is data collection. However, current underwater data collection schemes generally encounter problems such as high energy consumption and high latency. Furthermore, the application of multiple autonomous underwater vehicles (AUVs) has contributed to more problems of task assignment and load balancing. This leads to significant failure in data collections and controlling of spontaneous emergencies. To address these problems, a district partition based data collection algorithm with event dynamic competition in UASNs has been proposed. In this algorithm, the value of information (VoI) of the packet determines the priority of its transmission to the cluster head. The navigation position of the mobile sink and the area under the responsibility of each AUV are determined by the spatial region division. The path of the AUV in the subregion is then planned using reinforcement learning. Subsequently, the dynamic competition of multiple AUVs is used to handle emergency tasks. The simulation demonstrates that our proposed algorithm significantly reduces energy consumption to guarantee load balancing while reducing end-to-end transmission delay.

This paper exploits a quantum-empowered machine learning algorithm to enhance computation learning speed. We leverage quantum phenomena such as superposition and entanglement to work on large-scale multi-dimensional data represented by quantum states. Under stochastic behaviors and quantum uncertainty, we examine the offloading problem to maximize the computational task processing efficiency, considering the computation latency, energy consumption, and quantum network adaptability. From the Markov decision process, the paper proposes a novel quantum-empowered deep reinforcement learning (Qe-DRL) approach, combining quantum computing theory and machine learning to achieve exploration and exploitation trade-off via quantum parallelism significantly. Furthermore, we develop a modified Grover’s algorithm with exponential convergence speed to provide a searching strategy for transition quantum states probabilities. Simulation results establish the effectiveness of the proposed Qe-DRL algorithm and its superior computational learning speed. Our proposed Qe-DRL algorithm outperforms other benchmarks in terms of energy efficiency performance.

The time synchronization in vehicular ad hoc networks (VANETs) has gained significant attention in recent times. In this paper, we focus on the time synchronization in VANETs and propose an adaptive beacon time synchronization (ABTS) to enhance timing message synchronization in distributed large-scale VANETs. ABTS technique selects the best time synchronization pairs to decrease the number of timing messages transmitted. To guarantee the reliability of synchronization, the clock offset of the connected vehicles periodically readjusted to provide a better degree of synchronization accuracy with minimum energy consumption. Based on two-way timing message synchronization, we derive maximum likelihood (ML) estimation and its equivalent Cramer-Rao lower bound (CRLB) for clock offset design in the generalized sender-to-receiver system by assuming a Gaussian noise model. We propose node pair selection algorithms to enhance pairwise beacon message timing synchronization. The simulation results validated that our proposed ABTS technique performs better than other protocols in terms of synchronization accuracy, the rate of convergence and energy efficiency.

Source location privacy (SLP) protection is an important means of security protection in wireless sensor networks (WSNs). With the development of underwater acoustic sensor networks (UASNs), security and privacy have attracted increasing attention. In this study, we incorporated SLP into UASNs as the basis for a novel stratification-based source location privacy (SSLP) scheme. In the SSLP scheme, SLP is protected through the cooperation of autonomous underwater vehicles (AUVs) in each network layer. Because fake source nodes and fake data streams are commonly used in WSNs, methods that have similar functions in UASNs are required. Hence, we incorporate a fake source node into the underwater cluster structure to add randomness to the underwater network. Furthermore, fake data streams have been included within the AUV data collection and transmission for each cluster. Simulation results confirm that the SSLP scheme offers improved security in comparison with existing underwater data transmission schemes.

We investigate the joint optimization problem of stochastic computation offloading, content caching strategy, and dynamic resource allocation to maximize the energy efficiency of mobile edge computing in Internet-of-Things. Specifically, we propose a quantum deep reinforcement learning algorithm to exponentially increase the caching learning speed and content caching delivery efficiency in multi-dimensional continuous and large action spaces. Furthermore, we utilize the modified Grover’s algorithm with faster computation time to improve the processing efficiency and data-content retrieval for transition quantum state probabilities. The numerical results show that our proposed quantum machine learning scheme significantly outperforms other benchmarks in terms of energy-efficiency maximization subject to transmission power, energy consumption, and transmission latency.