Recently, the growing of deep space explorations has attracted notable interests on interplanetary network (IPN), which is the key infrastructure for communications across vast distances in the solar system. However, the unique characteristics of IPN pose numerous unexplored challenges for interplanetary data transfers (IP-DTs), i.e., the challenges that existing schemes developed for Earth-based networks are ill-equipped to handle. To address these challenges, we first propose a novel distributed algorithm that leverages the Lyapunov optimization to jointly optimize the routing, scheduling and rate control of IP-DTs at each node. Specifically, our proposal adaptively optimizes the data-rate and bundle scheduling at each output port of a node, significantly improving the end-to-end (E2E) latency and delivery ratio of IP-DTs under a long-term energy constraint. Then, we further explore the heterogeneity of IPN to introduce limited state information exchange among nodes, and devise mechanisms for generating and disseminating state messages to facilitate timely adjustments of routing and scheduling schemes in response to unexpected link disruptions and traffic surges. Simulations verify the advantages of our proposal over the state-of-the-arts.

As deep space exploration missions grow in complexity, efficient data transfer in interplanetary networks (IPNs) becomes paramount. However, the vast distances, limited bandwidth, and dynamic nature of IPNs pose significant challenges for the routing and data scheduling of interplanetary data transfers (IP-DTs). To address these challenges, this work proposes a novel distributed, graph neural network (GNN) based multiagent deep reinforcement learning (DRL) approach that can jointly optimize the routing and scheduling of IP-DTs. Our proposal is based on the proximal policy optimization (PPO) framework along with the graph attention networks (GATs). We make the DRL agents for IPN nodes in each subnetwork around a celestial body learn and operate independently, for making intelligent routing and scheduling decisions to properly tradeoff between average end-to-end (E2E) latency and delivery ratio of IP-DTs while ensuring good scalability. Extensive simulations confirm that our proposal handles the routing and scheduling of IP-DTs much better than existing benchmarks. Further, by modifying the interplanetary overlay network (ION) software platform developed by NASA, we build a semi-physical IPN emulator based on Raspberry Pi boards, implement our proposal in it, and conduct experiments with real data transfers between IPN nodes. Experimental results verify that our proposal can work for practical IPNs without causing excessive overheads and prove its advantages.

Interplanetary networks (IPNs) are complex communication infrastructures used for data exchange among spacecrafts, rovers and ground stations. Due to the significant delay and uncertainty in communications, efficient routing and data scheduling of interplanetary data transfer (IP-DT) becomes crucial. With the increase of deep space (DS) exploration missions, it would be difficult for existing IPNs to cope with the growing of IP-DT demands. In this work, to improve the performance of IP-DTs in IPNs, we formulate an integer linear programming (ILP) model and design an effective fine-grained distributed routing and data scheduling (FD-RDS) algorithm based on it. We prove that the proposed algorithm is a polynomial-time 2-approximation algorithm for solving the ILP model. Extensive simulations show that our proposals can significantly improve the efficiency and reliability of IPNs. Specifically, our proposals outperforms known benchmarks in terms of both the delivery ratio and E2E latency of IP-DTs.

With the fast development of deep space exploration missions, the data transfer in interplanetary networks (IPNs) is gaining increasing attention. In this work, we propose a deep reinforcement learning (DRL) based routing and data scheduling approach, which leverages a multi-agent setup for distributed operations and aims to balance the trade-off between average end-to-end (E2E) latency and delivery ratio of interplanetary data transfers (IP-DTs) well. Specifically, DRL agents based on asynchronous advantage actor-critic (A3C) are deployed on each IPN node to handle the routing and data scheduling of IP-DTs there separately. Simulation results confirm that our proposal can handle the routing and data scheduling of IP-DTs more adaptively and balance the tradeoff between the delivery ratio and average E2E latency better than the benchmarks.

Nowadays, the booming of emerging network services have shifted the major traffic pattern in metro-aggregation networks from point-to-point (P2P) to hub-and-spoke (H&S). Hence, it will be promising to plan metro-aggregation networks with point-to-multipoint coherent optical transceivers (P2MP-TRXs). This work studies how to plan a survivable wavelength-switched optical network (WSON) with P2MP-TRXs and shared backup path protection (SBPP) to address single-link failures. We formulate an integer linear programming (ILP) model to place P2MP-TRXs, assign sub-carriers (SCs) to P2MP-TRXs, and calculate routing and spectrum assignment (RSA) for the working/backup lightpath between each hub-leaf P2MP-TRX pair, such that traffic demands can be satisfied with the minimum cost. A heuristic based on adaptive demand grouping (ADG) is also proposed to solve the problem time-efficiently. Extensive simulations confirmed the performance of our proposals.

With the advances on human’s exploration of the universe, interplanetary networks (IPNs) are attracting more and more research interests. However, the unique characteristics of IPNs make many of the networking technologies on Earth not applicable. In this work, we design a routing and data scheduling algorithm that can make interplanetary data transfers (IP-DTs) more scalable and robust. Specifically, we propose an online approach to schedule and route IP-DTs in the distributed way, by leveraging the Lyapunov optimization. With extensive simulations, we show that our proposed algorithm can optimize the performance of IP-DTs with only the information about local queues on each node in an IPN. The simulation results also verify that our algorithm outperforms the existing ones significantly in terms of the average E2E latency of IP-DTs, and properly adjusts the tradeoff between average E2E latency and delivery ratio.

The service provisioning in multi-domain software-defined elastic optical networks (SD-EONs) is an interesting but difficult problem to tackle, because the basic problem of lightpath provisioning, i.e., the routing and spectrum assignment (RSA), is$\mathcal {NP}$-hard, and each domain is owned and operated by a different carrier. Therefore, even though numerous RSA heuristics have been proposed, there does not exist a universal winner that can always achieve the lowest blocking probability in all the scenarios of a multi-domain SD-EON. This motivates us to revisit the inter-domain provisioning problem in this paper by leveraging deep reinforcement learning (DRL). Specifically, we propose DeepCoop, which is an inter-domain service framework that uses multiple cooperative DRL agents to achieve scalable network automation in a multi-domain SD-EON. DeepCoop employs a DRL agent in each domain to optimize intra-domain service provisioning, while a domain-level path computation element (PCE) is introduced to obtain the sequence of the domains to go through for each lightpath request. By sharing a restricted amount of information among each other, the DRL agents can make their decisions distributedly. To ensure scalability and universality, we design the action space of each DRL agent based on well-known RSA heuristics, and architect the agents based on the soft actor-critic (SAC) scenario. We run extensive simulations to evaluate DeepCoop, and the results show that DeepCoop can adapt to the dynamic environment in a multi-domain SD-EON to always select the best RSA heuristic for minimizing blocking probability, and it outperforms the existing algorithms on inter-domain provisioning in various scenarios. Moreover, we verify that the distributed training implemented in DeepCoop ensures its universality and scalability (i.e., its training and operation do not depend on the topology of the SD-EON).