Semantic communication (SemCom), a paradigm central to the next generation task-oriented vision, relies on a shared Knowledge Base (KB) between the transmitter and receiver. However, the prevalent assumption of a static KB is frequently invalidated in dynamic real-world environments, where KB "staleness" precipitates a collapse in semantic efficiency. This introduces a critical trade-off: either continue transmission with a suboptimal, stale KB, or allocate scarce wireless resources to a knowledge consensus protocol to update the KB, thereby incurring a significant opportunity cost. This paper addresses this dynamic resource allocation problem. We are the first to establish a system model that explicitly quantifies knowledge staleness K(t) as a state variable and models the update procedure as a resource-consuming consensus task. We formulate this trade-off as a complex, NP-hard 0-1 Mixed-Integer Non-Linear Program (MINLP), which uniquely incorporates the fixed activation costs associated with initiating the consensus protocol. To solve this intractable problem, we propose a low-complexity online control framework based on model predictive control (MPC), which embeds a novel heuristic algorithm termed iterative marginal cost allocation (IMCA). Simulation results demonstrate that the proposed MPC-IMCA framework significantly outperforms static Greedy and Periodic Update baselines in long-term cumulative semantic utility, exhibiting robust adaptability to varying environmental dynamics (δd) and update workloads (DKB).

Semantic communication (SemCom) shifts the focus from bit-level accuracy to the preservation of meaning, enabling more efficient and robust transmission. To achieve a high utilization of the wireless channel in SemCom, in this paper, we propose a channel assignment approach for polar code-based SemCom that allocates polarized channels according to semantic importance. Specifically, by combining eye-tracking data with semantic segmentation, we define two metrics that capture the contribution and correlation of semantic entities within an image. Leveraging these semantic metrics and polarized channel reliabilities, we formulate a constrained 0-1 optimization problem for polarized channel assignment and develop a priority-based algorithm that dynamically prioritizes semantically important content. Simulation results demonstrate that our method significantly outperforms the traditional channel allocation policy, especially under harsh channel conditions, by preserving critical visual information while reducing overall transmission redundancy.

The integration of semantic communication (SemCom) with non-orthogonal multiple access (NOMA) presents a promising approach to enhance spectrum efficiency and system capacity. SemCom focuses on accurate meaning delivery with less bits, while NOMA enables simultaneous access for multiple users on the same frequency, maximizing resource utilization. However, power allocation in NOMA-based SemCom systems is quite challenging as it should accommodate not only channel conditions and interference management but also the characteristics of semantic information and service requirements. In this paper, we investigate the power allocation strategy for NOMA-based SemCom systems, with the aim to maximize system throughput in semantic unit (STU). Successive interference cancellation requirements and resource budgets are taken into account as the constraints. To address this problem, we propose a modified water filling-based algorithm enhancing both STU and fairness. Simulation results demonstrate the superiority of our proposed algorithm in terms of STU performance and fairness compared to two existing baseline strategies.

Several wireless networking problems are often posed as 0-1 mixed optimization problems, which involve binary variables (e.g., selection of access points, channels, and tasks) and continuous variables (e.g., allocation of bandwidth, power, and computing resources). Traditional optimization methods as well as reinforcement learning (RL) algorithms have been widely exploited to solve these problems under different network scenarios. However, solving such problems becomes more challenging when dealing with a large network scale, multi-dimensional radio resources, and diversified service requirements. To this end, in this paper, a unified framework that combines RL and optimization theory is proposed to solve 0-1 mixed optimization problems in wireless networks. First, RL is used to capture the process of solving binary variables as a sequential decision-making task. During the decision-making steps, the binary (0-1) variables are relaxed and, then, a relaxed problem is solved to obtain a relaxed solution, which serves as prior information to guide RL searching policy. Then, at the end of decision-making process, the search policy is updated via suboptimal objective value based on decisions made. The performance bound and convergence guarantees of the proposed framework are then proven theoretically. An extension of this approach is provided to solve problems with a non-convex objective function and/or non-convex constraints. Numerical results show that the proposed approach reduces the convergence time by about 30% over B&B in small-scale problems with slightly higher objective values. In large-scale scenarios, it can improve the normalized objective values by 20% over RL with a shorter convergence time.

Semantic communication (SemCom) has recently been considered a promising solution for the inevitable crisis of scarce communication resources. This trend stimulates us to explore the potential of applying SemCom to vehicular networks, which normally consume a tremendous amount of resources to achieve stringent requirements on high reliability and low latency. Unfortunately, the unique background knowledge matching mechanism in SemCom makes it challenging to realize efficient vehicle-to-vehicle service provisioning for multiple users at the same time. To this end, this paper identifies and jointly addresses two fundamental problems of knowledge base construction (KBC) and vehicle service pairing (VSP) inherently existing in SemCom-enabled vehicular networks. Concretely, we first derive the knowledge matching based queuing latency specific for semantic data packets, and then formulate a latency-minimization problem subject to several KBC and VSP related reliability constraints. Afterward, a SemCom-empowered Service Supplying Solution (S4) is proposed along with the theoretical analysis of its optimality guarantee. Simulation results demonstrate the superiority of S4 in terms of average queuing latency, semantic data packet throughput, and user knowledge preference satisfaction compared with two different benchmarks.