Unmanned aerial vehicle (UAV) swarms have significant advantages in terms of cost, number, and intelligence, constituting a serious threat to traditional frigate air defense systems. Ship-borne short-range anti-air weapons undertake terminal defense tasks against UAV swarms. In traditional air defense fire control systems, a dynamic weapon-target assignment (DWTA) is disassembled into several static weapon target assignments (SWTAs), but the relationship between DWTAs and SWTAs is not supported by effective analytical proof. Based on the combat scenario between a frigate and UAV swarms, a model-based reinforcement learning framework was established, and a DWAT problem was disassembled into several static combination optimization (SCO) problems by means of the dynamic programming method. In addition, several variable neighborhood search (VNS) operators and an opposition-based learning (OBL) operator were designed to enhance the global search ability of the original Grey Wolf Optimizer (GWO), thereby solving SCO problems. An improved grey wolf algorithm based on reinforcement learning (RL-IGWO) was established for solving DWTA problems in the defense of frigates against UAV swarms. The experimental results show that RL-IGWO had obvious advantages in both the decision making time and solution quality.

Missing link prediction technology (MLP) is always a hot research area in the field of complex networks, and it has been extensively utilized in UAV swarm network reconstruction recently. UAV swarm is an artificial network with strong randomness, in the face of which prediction methods based on network similarity often perform poorly. To solve those problems, this paper proposes a Multi Kernel Learning algorithm with a multi-strategy grey wolf optimizer based on time series (MSGWO-MKL-SVM). The Multiple Kernel Learning (MKL) method is adopted in this algorithm to extract the advanced features of time series, and the Support Vector Machine (SVM) algorithm is used to determine the hyperplane of threshold value in nonlinear high dimensional space. Besides that, we propose a new measurable indicator of Multiple Kernel Learning based on cluster, transforming a Multiple Kernel Learning problem into a multi-objective optimization problem. Some adaptive neighborhood strategies are used to enhance the global searching ability of grey wolf optimizer algorithm (GWO). Comparison experiments were conducted on the standard UCI datasets and the professional UAV swarm datasets. The classification accuracy of MSGWO-MKL-SVM on UCI datasets is improved by 6.2% on average, and the link prediction accuracy of MSGWO-MKL-SVM on professional UAV swarm datasets is improved by 25.9% on average.

With the rapid development of intelligent manufacturing technology, Wireless Sensor Networks have been widely implemented in increasingly more industries, while gradually getting mature. However, the topology control ability and power consumption have limited their scale and performance for a long time. Therefore, in order to improve the robustness of their network structures and prolong their life cycles, this study explores Energy Network Topology Control based on Power Optimization. A topology structure model of an Energy Network was established based on the graph theory, and certain indicators of network connectivity and energy consumption were adopted as objective functions. Eventually, the problem was transformed into a multi-objective combinational optimization issue. Based on the characters of energy harvesting wireless sensor network, this study also proposed a new Distributed Hybird Strategy Grey Wolf Optimizer algorithm (DHS-GWO). The design of the distributed architecture and addition of parallel search operators greatly improved the solving speed and operation quality of the original GWO algorithm. A distributed protocol was designed to eliminate the conflicts generated in the process of distributed decisions and generate a quasi-global solution. Experimental results proved the effectiveness and competitiveness of the proposed method in terms of performance and running speed. In numerical experiments, the running time of DHS-GWO is decreased by 81.5% on average, and the transmitting power consumption of DHS-GWO is declined by 51.9% on average.