Bo Gu

Xu Zhang, Ziqi Lin, Shimin Gong et al.

Long Range (LoRa) wireless technology, characterized by low power consumption and a long communication range, is regarded as one of the enabling technologies for the Industrial Internet of Things (IIoT). However, as the network scale increases, the energy efficiency (EE) of LoRa networks decreases sharply due to severe packet collisions. To address this issue, it is essential to appropriately assign transmission parameters such as the spreading factor and transmission power for each end device (ED). However, due to the sporadic traffic and low duty cycle of LoRa networks, evaluating the system EE performance under different parameter settings is time-consuming. Therefore, we first formulate an analytical model to calculate the system EE. On this basis, we propose a transmission parameter allocation algorithm based on multiagent reinforcement learning (MALoRa) with the aim of maximizing the system EE of LoRa networks. Notably, MALoRa employs an attention mechanism to guide each ED to better learn how much ''attention'' should be given to the parameter assignments for relevant EDs when seeking to improve the system EE. Simulation results demonstrate that MALoRa significantly improves the system EE compared with baseline algorithms with an acceptable degradation in packet delivery rate (PDR).

Songhan Zhao, Shimin Gong, Bo Gu et al.

This paper explores a reconfigurable intelligent surface (RIS)-assisted and semantic-aware wireless network, where multiple semantic users (SUs) transmit semantic information to an access point (AP) using the non-orthogonal multiple access (NOMA) method. The RIS reconfigures channel conditions, while semantic extraction reshapes traffic demands, providing enhanced control flexibility for NOMA transmissions. To enable efficient long-term resource allocation, we propose a deferrable semantic extraction scheme that can distribute the semantic extraction tasks across multiple time slots. We formulate a long-term energy efficiency maximization problem by jointly optimizing the RIS's passive beamforming, the SUs' semantic extraction, and the NOMA decoding order. Note that this problem involves multiple and coupled control variables, which can incur significant computational overhead in time-varying network environments. To support low-complexity online optimization, a deep reinforcement learning (DRL)-driven online optimization framework is developed. Specifically, the DRL module facilitates the adaptive selection and optimization of the most suitable option from traffic reshaping, channel reconfiguration, or NOMA decoding order assignment based on the dynamic network status. Numerical results demonstrate that the deferrable semantic extraction scheme significantly improves the long-term energy efficiency. Meanwhile, the DRL-driven online optimization framework effectively reduces the running time while maintaining superior learning performance compared to state-of-the-art methods.

Songhan Zhao, Shimin Gong, Bo Gu et al.

In this paper, we investigate a generative artificial intelligence (GAI)-assisted semantic communication framework for non-orthogonal multiple access (NOMA)-based image transmissions. Semantic users (SUs) extract cross-modal semantic features from the raw images, which are then used for image recovery by leveraging a GAI model. The GAI enhances the generalization and recovery of semantic image transmissions, while NOMA efficiently allocates transmission capacities to SUs based on their traffic demands. Thus, the semantic extraction and transmission control jointly affect both semantic recovery performance and transmission overhead. We maximize a weighted performance of transmission latency and semantic recovery accuracy by jointly optimizing the semantic feature selection at the semantic level, as well as the receive beamforming and NOMA decoding order at the transmission level. To reduce potential redundancy in semantic features and improve optimization efficiency, we develop an importance-aware and model-driven proximal policy optimization (IM-PPO) framework. Specifically, we quantify and retain high-importance semantic features to enhance the learning efficiency of PPO, while model-based optimization methods are used to adapt the transmission control variables. Numerical results validate that the joint adjustment of the semantic feature selection and the transmission control significantly improves the semantic recovery accuracy and the transmission latency performance. Moreover, the IM-PPO framework effectively leverages the model information to improve the learning efficiency compared to benchmark methods.

Yiming Chen, Xingyuan Hu, Bo Gu et al.

In mobile edge computing systems, base stations (BSs) equipped with edge servers can provide computing services to users to reduce their task execution time. However, there is always a conflict of interest between the BS and users. The BS prices the service programs based on user demand to maximize its own profit, while the users determine their offloading strategies based on the prices to minimize their costs. Moreover, service programs need to be pre-cached to meet immediate computing needs. Due to the limited caching capacity and variations in service program popularity, the BS must dynamically select which service programs to cache. Since service caching and pricing have different needs for adjustment time granularities, we propose a two-time scale framework to jointly optimize service caching, pricing and task offloading. For the large time scale, we propose a game-nested deep reinforcement learning algorithm to dynamically adjust service caching according to the estimated popularity information. For the small time scale, by modeling the interaction between the BS and users as a two-stage game, we prove the existence of the equilibrium under incomplete information and then derive the optimal pricing and offloading strategies. Extensive simulations based on a real-world dataset demonstrate the efficiency of the proposed approach.

Jieting Yuan, Songhan Zhao, Ye Xue et al.

This paper focuses on secure communications in UAV-assisted wireless networks, which comprise multiple legitimate UAVs (LE-UAVs) and an intelligent eavesdropping UAV (EA-UAV). The intelligent EA-UAV can observe the LE-UAVs'transmission strategies and adaptively adjust its trajectory to maximize information interception. To counter this threat, we propose a mode-switching scheme that enables LE-UAVs to dynamically switch between the data transmission and jamming modes, thereby balancing data collection efficiency and communication security. However, acquiring full global network state information for LE-UAVs' decision-making incurs significant overhead, as the network state is highly dynamic and time-varying. To address this challenge, we propose a digital twin-enabled simultaneous learning and modeling (DT-SLAM) framework that allows LE-UAVs to learn policies efficiently within the DT, thereby avoiding frequent interactions with the real environment. To capture the competitive relationship between the EA-UAV and the LE-UAVs, we model their interactions as a multi-stage Stackelberg game and jointly optimize the GUs' transmission control, UAVs' trajectory planning, mode selection, and network formation to maximize overall secure throughput. Considering potential model mismatch between the DT and the real environment, we propose a robust proximal policy optimization (RPPO) algorithm that encourages LE-UAVs to explore service regions with higher uncertainty. Numerical results demonstrate that the proposed DT-SLAM framework effectively supports the learning process. Meanwhile, the RPPO algorithm converges about 12% faster and the secure throughput can be increased by 8.6% compared to benchmark methods.

Haidong Wang, Songhan Zhao, Bo Gu et al.

In this paper, we explore a joint source and reconfigurable intelligent surface (RIS)-assisted channel encoding (JSRE) framework for multi-user semantic communications, where a deep neural network (DNN) extracts semantic features for all users and the RIS provides channel orthogonality, enabling a unified semantic encoding-decoding design. We aim to maximize the overall energy efficiency of semantic communications across all users by jointly optimizing the user scheduling, the RIS's phase shifts, and the semantic compression ratio. Although this joint optimization problem can be addressed using conventional deep reinforcement learning (DRL) methods, evaluating semantic similarity typically relies on extensive real environment interactions, which can incur heavy computational overhead during training. To address this challenge, we propose a truncated DRL (T-DRL) framework, where a DNN-based semantic similarity estimator is developed to rapidly estimate the similarity score. Moreover, the user scheduling strategy is tightly coupled with the semantic model configuration. To exploit this relationship, we further propose a semantic model caching mechanism that stores and reuses fine-tuned semantic models corresponding to different scheduling decisions. A Transformer-based actor network is employed within the DRL framework to dynamically generate action space conditioned on the current caching state. This avoids redundant retraining and further accelerates the convergence of the learning process. Numerical results demonstrate that the proposed JSRE framework significantly improves the system energy efficiency compared with the baseline methods. By training fewer semantic models, the proposed T-DRL framework significantly enhances the learning efficiency.

Bo Gu, Zhikang Zhang, Zizhuang Wei et al.

Recent multimodal large language models (MLLMs) have made remarkable progress in visual understanding and language-based reasoning, yet they lack a persistent world-centered representation for spatially consistent reasoning in 3D environments. Inspired by the mammalian dual-stream system, where semantic and spatial cues are processed separately and integrated into an allocentric cognitive map, we propose SpaceMind++, a video MLLM architecture that explicitly builds a voxelized cognitive map from RGB videos. This map reorganizes fragmented egocentric observations into a shared 3D metric representation, enabling the model to preserve object permanence and spatial topology across changing viewpoints. To make this allocentric representation usable by a pretrained video MLLM without disrupting its native visual-token interface, we introduce Coordinate-Guided Deep Iterative Fusion, a new mechanism that relays map-level spatial knowledge back into the original 2D visual features. This fusion is explicitly guided by coordinate embeddings and 3D Rotary Positional Encoding, which ground semantic interactions in metric 3D space, resembling the entorhinal binding of sensory features to metric space. Extensive experiments show that SpaceMind++ achieves new state-of-the-art performance on VSI-Bench. Furthermore, it demonstrates superior out-of-distribution generalization on SPBench, SITE-Bench, and SPAR-Bench, underscoring its robustness in unseen 3D environments.