An inter-satellite communication network of satellite swarm (ICNS) is created if the members of a satellite swarm communicate with each other via inter-satellite links (ISLs). ICNS can be constructed using the theory of complex networks. A link community is defined as two satellites between which the ISL has been established. The satellite swarm, whose members have not established ISLs, is modeled as a pre-link network (PLN). The edge of a PLN is described as a candidate for the link community. Consequently, an ICNS can be constructed by collecting combinations of candidates for link communities (CCLC) based on PLN and then by selecting one of these. An algorithm is designed to take a sample of all CCLCs. A new structural entropy of networks is developed to evaluate a CCLC. The CCLC with a maximum structural entropy in the CCLC sample will be selected to become the edge set of the ICNS. An improvement method was proposed to ensure that the ICNS remains a dynamic connected network by preventing each satellite from establishing an ISL with the same satellite. The simulations demonstrated that the proposed method outperformed the benchmark methods, and it is necessary to adopt the improvement method.

In order to abstract away a network model from some real-world networks, such as navigation satellite networks and mobile call networks, we proposed an Isochronal-Evolution Random Matching Network (IERMN) model. An IERMN is a dynamic network that evolves isochronally and has a collection of edges that are pairwise disjoint at any point in time. We then investigated the traffic dynamics in IERMNs whose main research topic is packet transmission. When a vertex of an IERMN plans a path for a packet, it is permitted to delay the sending of the packet to make the path shorter. We designed a routing decision-making algorithm for vertices based on replanning. Since the IERMN has a specific topology, we developed two suitable routing strategies: the Least Delay Path with Minimum Hop (LDPMH) routing strategy and the Least Hop Path with Minimum Delay (LHPMD) routing strategy. An LDPMH is planned by a binary search tree and an LHPMD is planned by an ordered tree. The simulation results show that the LHPMD routing strategy outperformed the LDPMH routing strategy in terms of the critical packet generation rate, number of delivered packets, packet delivery ratio, and average posterior path lengths.

As knowledge and data increase in scale and complexity, it is more difficult to apply these two key assets to achieve optimal effectiveness in engagement simulation. The aim of this study was to investigate the techniques of knowledge and data integration with respect to the development of smart agents to predict accurate behaviors in tactical engagements. To reduce the complexity of combat behavior representation, with respect to the functions, we represented subject matter expert operational knowledge by proposing multiple levels of cascaded hierarchical structure, namely, the function decision tree, to increase the readability and maintainability of the behavioral model. For decision points in a behavioral model, smart agents can be trained based on data samples collected from rounds of constructive simulations which provide validated physical models and tactical principles. As a proof of concept, we constructed a simulation testbed of multi-warhead ballistic missile penetration, which generated 129,600 constructive simulations over a total of 84 h. Thereafter, we selected 5817 data samples (i.e. ~4.5% of the simulations) using an operational metric of total rewards exceeding 100. The data samples are used to train an artificial neural network and then this network is used to develop a deep reinforcement learning agent. The results revealed that the training process iterated nearly 17,000 epochs until the policy loss decreased to an acceptable low value. The smart agent increased the ratio of ballistic missile target hits by 18.96%, a significant increase when compared with the traditional rule-based behavioral model.

Dynamic multi-target assignment is a key technology that needs to be supported in order to improve the strike effectiveness during the coordinated attack of the missile swarm, and it is of great significance for improving the intelligence level of the new generation of strike weapon groups. Changes in ballistic trajectory during the penetration of multi-warhead missiles may cause the original target assignment scheme to no longer be optimal. Therefore, reassigning targets based on the real-time position of the warhead plays an important role in improving the effectiveness of the strike. In this paper, the dynamic multi-target assignment decision modeling method combining combat simulation and deep reinforcement learning was discussed, and an intelligent decision-making training framework for multitarget assignment was designed based on deep reinforcement learning. In conjunction with the typical combat cases, the warhead combat process was also divided into the penetration phase and the multi-target assignment phase, the model framework and reward function against the multi-target assignment of the missile were devised, and the SAC algorithm was employed to conduct application research on intelligent decision modeling for multi-target assignment. Preliminary test results suggest that the intelligent decisionmaking model based on deep reinforcement learning provides better combat effects than the traditional decision model based on knowledge engineering.INDEX TERMS Deep reinforcement learning, combat simulation, intelligent decision-making, multi-target assignment.

No abstract