RESUMO
In this article, a novel cross-domain knowledge transfer method is implemented to optimize the tradeoff between energy consumption and information freshness for all pieces of equipment powered by heterogeneous energy sources within smart factory. Three distinct groups of use cases are considered, each utilizing a different energy source: grid power, green energy source, and mixed energy sources. Differing from mainstream algorithms that require consistency among groups, the proposed method enables knowledge transfer even across varying state and/or action spaces. With the advantage of multiple layers of knowledge extraction, a lightweight knowledge transfer is achieved without the need for neural networks. This facilitates broader applications in self-sustainable wireless networks. Simulation results reveal a notable improvement in the 'warm start' policy for each equipment, manifesting as a 51.32% increase in initial reward compared to a random policy approach.
RESUMO
A proactive mobile network (PMN) is a novel architecture enabling extremely low-latency communication. This architecture employs an open-loop transmission mode that prohibits all real-time control feedback processes and employs virtual cell technology to allocate resources non-exclusively to users. However, such a design also results in significant potential user interference and worsens the communication's reliability. In this paper, we propose introducing multi-reconfigurable intelligent surface (RIS) technology into the downlink process of the PMN to increase the network's capacity against interference. Since the PMN environment is complex and time varying and accurate channel state information cannot be acquired in real time, it is challenging to manage RISs to service the PMN effectively. We begin by formulating an optimization problem for RIS phase shifts and reflection coefficients. Furthermore, motivated by recent developments in deep reinforcement learning (DRL), we propose an asynchronous advantage actor-critic (A3C)-based method for solving the problem by appropriately designing the action space, state space, and reward function. Simulation results indicate that deploying RISs within a region can significantly facilitate interference suppression. The proposed A3C-based scheme can achieve a higher capacity than baseline schemes and approach the upper limit as the number of RISs increases.
RESUMO
The demand for bandwidth-intensive and delay-sensitive services is surging daily with the development of 5G technology, resulting in fierce competition for scarce radio resources. Power domain Nonorthogonal Multiple Access (NOMA) technologies can dramatically improve system capacity and spectrum efficiency. Unlike existing NOMA scheduling that mainly focuses on fairness, this paper proposes a power control solution for uplink hybrid OMA and PD-NOMA in dual dynamic environments: dynamic and imperfect channel information together with the random user-specific hierarchical quality of service (QoS). This paper models the power control problem as a nonconvex stochastic, which aims to maximize system energy efficiency while guaranteeing hierarchical user QoS requirements. Then, the problem is formulated as a partially observable Markov decision process (POMDP). Owing to the difficulty of modeling time-varying scenes, the urgency of fast convergency, the adaptability in a dynamic environment, and the continuity of the variables, a Deep Reinforcement Learning (DRL)-based method is proposed. This paper also transforms the hierarchical QoS constraint under the NOMA serial interference cancellation (SIC) scene to fit DRL. The simulation results verify the effectiveness and robustness of the proposed algorithm under a dual uncertain environment. As compared with the baseline Particle Swarm Optimization algorithm (PSO), the proposed DRL-based method has demonstrated satisfying performance.