The rapid advancement of AI-generated content (AIGC) is poised to reshape content delivery, by enabling AIGC capabilities at the network edge or directly on end-user devices. This will allow content requests to be satisfied with AIGC based on prompts, rather than transmitting the original content. Each option presents unique trade-offs. On-device AIGC minimizes network traffic by transmitting only prompts, but it produces lower content quality than on-edge AIGC, which supports larger AI models. AIGC on the edge, in turn, results in lower quality than the original content. Delivering the original content requires more resource on radio access (and backhaul if not cached), while on-edge AIGC consumes computing power. To optimally exploit these trade-offs, we formulate a utility maximization problem where for each content the system can opt for the original content, on-edge AIGC, or on-device AIGC, accounting for backhaul capacity, computational resources, and radio access constraints. For this discrete optimization problem, we prove that, by applying Lagrangian multipliers to the three resource constraints, the problem relaxation can be efficiently solved to optimality. We then propose a solution approach that combines the problem relaxation with an algorithm for reaching feasible solutions of the overall problem. Simulation results demonstrate that our approach outperforms the baseline strategies and the solutions are close to the global optimum.

Federated Learning (FL) on low earth orbit (LEO) satellites represents a promising frontier for on-orbit edge intelligence. However, the inherent network dynamics and heterogeneity of datasets and resource across satellites pose challenges to efficient on-orbit FL. In this work, we model client selection and inter-satellite routing as a joint optimization problem. We derive and minimize an upper bound of the global empirical loss as the objective function, to enable fast convergence. We model the constraints of inter-satellite routing via time-varying graphs and network flow theory. We propose both exact and approximate solutions for the joint optimization problem. In addition, we formalize and prove the convergence property of our approach. Last, by simulation we demonstrate the efficiency and superiority of the proposed scheme for realistic satellite networking scenarios.

Passively cooled base stations (PCBSs) offer low deployment cost and energy consumption for the next generation networks. By its nature, however, dealing with the thermal issue becomes crucial. For an outdoor PCBS, a major challenge is that the heat dissipation is uncertain over time. We address this online temperature scheduling problem with uncertain parameters via adjustable robust optimization (ARO) embedded into a re-optimization framework. In each optimization instance, temperature pre-scheduling is done to achieve solution robustness, looking ahead into forthcoming time slots. The solution is adaptive with respect to the gradually realized heat dissipation. Interestingly, we prove that the robust temperature pre-scheduling problem can be addressed via solving a compact linear program (LP), even though the number of possible realizations of heat dissipation is infinite. Simulation results show that our algorithm achieves robustness as well as very good average performance.

Passively cooled base stations (PCBSs) are highly relevant for achieving better efficiency in cost and energy. However, dealing with the thermal issue via load management, particularly for outdoor deployment of PCBS, becomes crucial. This is a challenge because the heat dissipation efficiency is subject to (uncertain) fluctuation over time. Moreover, load management is an online decision-making problem by its nature. In this paper, we demonstrate that a reinforcement learning (RL) approach, specifically Soft Actor-Critic (SAC), enables to make a PCBS stay cool. The proposed approach has the capability of adapting the PCBS load to the time-varying heat dissipation. In addition, we propose a denial and reward mechanism to mitigate the risk of overheating from the exploration such that the proposed RL approach can be implemented directly in a practical environment, i.e., online RL. Numerical results demonstrate that the learning approach can achieve as much as 88.6% of the global optimum. This is impressive, as our approach is used in an online fashion to perform decision-making without the knowledge of future heat dissipation efficiency, whereas the global optimum is computed assuming the presence of oracle that fully eliminates uncertainty. This paper pioneers the approach to the online PCBSs load management problem.

In multi-access edge computing (MEC) systems, there are multiple local cache servers caching contents to satisfy the users’ requests, instead of letting the users download via the remote cloud server. In this paper, a multi-cell content scheduling problem (MCSP) in MEC systems is considered. Taking into account jointly the freshness of the cached contents and the traffic data costs, we study how to schedule content updates along time in a multi-cell setting. Different from single-cell scenarios, a user may have multiple candidate local cache servers, and thus the caching decisions in all cells must be jointly optimized. We first prove that MCSP is NP-hard, then we formulate MCSP using integer linear programming, by which the optimal scheduling can be obtained for small-scale instances. For problem solving of large scenarios, via a mathematical reformulation, we derive a scalable optimization algorithm based on repeated column generation. Our performance evaluation shows the effectiveness of the proposed algorithm in comparison to an off-the-shelf commercial solver and a popularity-based caching.

Caching popular contents at cell edge has been recognized as a promising way to facilitate rapid content delivery and alleviate backhaul burden. The content popularity is greatly influenced by recommendations by content providers. In this paper, we leverage this fact to jointly optimize caching and recommendation towards higher caching efficiency. We focus on both personalized and incumbent-aware recommendation. The incumbent content refers to the content that a user is currently browsing, resulted by the user's short-term interest. We model and formulate the resulting cache efficiency maximization problem subject to user satisfaction requirements. We prove the NP-hardness of the problem, and reformulate it using integer linear programming, enabling to solve optimally small-scale instances. Based on problem analysis with a graph representation, we derive three polynomial-time algorithms, where the recommendation sub-problem is solved to global optimum. Among these algorithms, the first two are based on sub-modularity, with$1-e^{-1}$approximation guarantee under mild conditions, while the last one is an alternation-based algorithm with fast convergence. Numerical results show the close-to-optimal performance of the proposed algorithms.

Performance degradation due to target deviation by, for example, drift or jitter, presents a significant issue to inter-satellite laser communications. In particular, with periodic acquisition for positioning the satellite receiver, deviation may arise in the time period between two consecutive acquisition operations. We propose a robust optimization approach to the problem. To solve the robust optimization problem, we deploy a process of alternately solving a decision maker’s problem and an adversarial problem. The former optimizes the divergence angle for a subset of the uncertainty set, whereas the latter is used to explore if the subset needs to be augmented. Simulation results show the approach leads to significantly more robust performance than using the divergence angle as if there is no deviation, or other ad-hoc schemes.

In multi-access edge computing (MEC) systems, there are several local cache servers caching contents to satisfy the users’ requests, instead of letting the users download via the remote cloud server. In this paper, a content scheduling problem (CSP) in MEC systems is considered. Taking into account jointly the freshness of the cached contents and the traffic data costs, we study how to schedule content updates along time in a multi-cell setting. Different from single-cell scenarios, a user may have multiple candidate cache servers, and thus all cells and their caching decisions must be jointly taken. We first prove that CSP is $\mathcal{N}\mathcal{P}$-hard, then we formulate CSP using integer linear programming. For problem solving, via a mathematical reformulation, we derive a column generation algorithm embedded into a rounding scheme. Our performance evaluation demonstrates that the solutions obtained are within 0.8% from global optimality.

Satellite communication network has the advantages of high, long and wide-area coverage. It becomes an important part of 5G network. Network-as-a-service requires real-time processing capability in orbit. In order to cope with this challenge, this paper proposes a flexible network slice support. The space-based edge computing system architecture and the resource management mechanism is designed. The resource allocation can be based on different QoS requirements according to the application scenario and business requirements. This paper models and simulates the satellite network and resource model system. The simulation results show that flexible network slice allocation can be performed according to the service QoS requirements, which can meet the bandwidth and computing resources requirements of different slices, reduce the delay, improve the throughput, reduce the network backhaul bandwidth pressure, and improve the comprehensive benefits of the satellite network.

With the development of space technology, it is an inevitable trend to construct a flexible and efficient computing system for space-based information network. The traditional single-satellite computing can't meet the increasing computing requirements, and the single-satellite resource utilization rate is unsatisfactory. This paper proposes a creative space-based cloud-fog computing architecture, which combines the cloud-fog computing technology with the space-based information network. This architecture is expected to change the traditional mode of data processing that relies on ground nodes by introducing the space-based edge cloud and fog satellites. It can also significantly improve the computing and the service capabilities of on-orbit satellites. Using this computing architecture can save the transmission bandwidth of satellite-ground links and improve the real-time performance of time-sensitive service processing, bringing inspirations and innovations to the development of space information networks. In this paper, we also propose some applied scenarios and implement a simulation for verifying this computing architecture.

The satellite communication network has the advantage of wide coverage and is one of the important development directions of fifth generation network. The traditional satellite data processing method is to transmit data to the ground data center for processing. There are problems such as large bandwidth pressure for the satellite link and poor real-time performance. Facing the increasing demand for on-board computing in satellite networks, building a flexible space-based edge system is an effective means to solve this problem. In this paper, SoC FPGA (System on Chip Field Programmable Gate Array) is proposed as a computing resource of the space-based edge network, and a unified service interface is provided for users. To maximize FPGA resource utilization, we studied the elastic scaling mechanism of FPGA resources. Finally, the computational performance and power consumption efficiency of the SoC FPGA computing platform are verified by experiments.