Past few years have witnessed the compelling applications of the blockchain technique in our daily life ranging from the financial market to health care. Considering the integration of the blockchain technique and the industrial Internet of Thing (IoT), blockchain may act as a distributed ledger for beneficially establishing a decentralized autonomous trading platform for industrial IoT (IIoT) networks. However, the power and computation constraints prevent IoT devices from directly participating in this Proof-of-Work (PoW) process. As a remedy, in this treatise, the cloud computing service is introduced into the blockchain platform for the sake of assisting to offload computational task from the IIoT network itself. In addition, we study the resource management and pricing problem between the cloud provider and miners. More explicitly, we model the interaction between the cloud provider and miners as a Stackelberg game, where the leader, i.e. cloud provider, makes the price first, and then miners act as the followers. Moreover, in order to find the Nash quilibrium of the proposed Stackelberg game, a multi-agent reinforcement learning algorithm is conceived for searching the near-optimal policy. Finally, extensive simulations are conducted to evaluate our proposed algorithm in comparison to some stateof-the-art schemes.

With the development of commercial off-the-shelf hardware, low Earth orbit (LEO) satellites are promising to provide flexible edge computing services. In this paper, we investigate a digital twin (DT)-empowered satellite-terrestrial cooperative edge computing network, where computation tasks from terrestrial users can be partially offloaded to the associated base station (BS) edge server, the associated LEO satellite edge server, and an adjacent LEO satellite edge server. We formulate a multi-tier computation offloading optimization problem to minimize the weighted sum of total system delay and satellite energy consumption, where a LEO-layer problem and a DT-layer problem are involved. The LEO-layer problem optimizes the three-tier computation resource allocation and task splitting ratio. From the multi-satellite network perspective, the DT-layer problem optimizes how many resources will be shared between adjacent satellites. We then propose a multi-agent double actors twin delayed deterministic policy gradient (MA-DATD3) algorithm to optimize the LEO-layer problem, and adopt a centralized training and decentralized execution (CTDE) paradigm. The proposed MA-DATD3 algorithm is extended to solve the DT-layer problem in a centralized way, and the resource sharing between adjacent satellites is optimized to maximize the time-averaged reward. Simulation results show that our algorithm achieves a better performance than the MADDPG algorithm, and effectively improves the computation offloading performance while balancing the energy consumption and the total delay.

To improve the energy efficiency for satellite downlink, a data offloading mechanism is studied for multi-cell satellite-terrestrial networks. Different services are first offloaded to the satellite-terrestrial terminal (STT) in each small cell and then forwarded to grounded users. By integrating the power allocation for satellite backhauling and the resource allocation for STT downlink, we aim to maximize the energy efficiency of data offloading in the multi-cell satellite-terrestrial networks. The problem is decomposed into two types of subproblems, where the downlink capacity in each cell, as well as the energy efficiency of satellite backhauling, are maximized. The optimal solution is approached by invoking a binary search aided algorithm, and simulation results demonstrate that the proposed algorithm effectively achieves the preferred energy-efficient allocation.

As a complement to terrestrial networks, low Earth orbit (LEO) satellite networks are promising to provide ubiquitous and continuous services. To accommodate the dynamic topology of LEO satellite networks and increasing traffic demands, this paper proposes a distributed routing approach to optimize the end-to-end delay relying on the multi-agent deep reinforcement learning(MADRL), where each satellite node is deployed with an autonomous agent and makes its real-time next-hop decisions independently with local observation information. To promote the inner cooperation between decentralized agents, a centralized training scheme with a unified load-balancing reward is utilized by adopting a novel multi-agent Transformer-MIX architecture. Moreover, to derive a better decision for each agent, we design an attention-involved agent network to capture more hidden information, and a Transformer-based parameter recurrent mechanism to generate the joint action-value function is used to enhance a more stable training. The simulation results indicate that our proposed scheme achieves faster convergence and demonstrates superior performance across several key performance metrics compared to existing benchmark schemes. Specifically, when the inter-satellite link (ISL) failure rate in the network reaches 18%, our scheme achieves a reduction in end-to-end delay by 13.6% and an increase in packet successful delivery rate by 5.4% compared to the benchmark schemes.

To enhance the efficient content dissemination in terrestrial-satellite networks, we investigate the joint content placement and multi-hop delivery problem to reduce the average path length for content delivery. In the considered architecture, contents can be shared in multi-hop terrestrial networks while each content is offloaded to only one terrestrial user via the satellite. Considering both content popularity and channel conditions, content placement is performed by optimizing the satellite downlink resource allocation where a distance-sensitive popularity parameter is introduced. Moreover, we formulate a path length minimization problem for content delivery in terrestrial networks, and a relay-aided multi-hop routing algorithm is proposed. Our simulation results show that the proposed scheme forcefully strikes a balance between terrestrial network backlogs and satellite downlink throughput, and achieves a better multi-hop delivery performance.

Low earth orbit (LEO) satellite networks are promising to carry out edge computing and reduce the service latency in future 6 G networks. Meanwhile, the microservice architecture provides a lightweight and flexible approach for network function deployment in satellite edge computing networks by splitting complex applications into multiple microservices. In satellite edge computing networks, a brand new problem is how to deploy various types of microservices with service function chain (SFC) constraints onto appropriate satellites to efficiently utilize limited on-board resources and reduce the service latency. In this paper, a distributed microservice deployment strategy in satellite edge computing networks is proposed by taking into account time-varying satellite network topology and diverse satellite resources. Specifically, we formulate the deployment problem as a partially observable Markov decision process (POMDP) to minimize the load imbalance as well as the service latency. A distributed multi-agent reinforcement learning (DMARL) scheme is proposed for learning a dynamic deployment strategy. Furthermore, to accommodate more microservices in SFC, a novel attention-based actor-critic strategy is designed to significantly accelerate the convergence of network training. Simulation results demonstrate that the proposed DMARL scheme can achieve a superior performance.