Task assignment in ground-to-air confrontation based on multiagent deep reinforcement learning

The scale of ground-to-air confrontation task assignments is large and needs to deal with many concurrent task assignments and random events.Aiming at the problems where existing task assignment methods are applied to ground-to-air confrontation,there is low efficiency in dealing with complex tasks,and there are interactive conflicts in multiagent systems.This study proposes a multiagent architecture based on a one-general agent with multiple narrow agents(OGMN)to reduce task assignment conflicts.Considering the slow speed of traditional dynamic task assignment algorithms,this paper proposes the proximal policy optimization for task assignment of general and narrow agents(PPOTAGNA)algorithm.The algorithm based on the idea of the optimal assignment strategy algorithm and combined with the training framework of deep reinforcement learning(DRL)adds a multihead attention mechanism and a stage reward mechanism to the bilateral band clipping PPO algorithm to solve the problem of low training efficiency.Finally,simulation experiments are carried out in the digital battlefield.The multiagent architecture based on OGMN combined with the PPO-TAGNA algorithm can obtain higher rewards faster and has a higher win ratio.By analyzing agent behavior,the efficiency,superiority and rationality of resource utilization of this method are verified.

Soil Nature Effect Investigation on the Ground-to-Air Heat Exchanger for the Passive Cooling of Rooms

The building sector consumes much energy either for cooling or heating and is associated to greenhouse gas emissions. To meet energy and environmental challenges, the use of ground-to-air heat exchangers for preheating and cooling buildings has recently received considerable attention. They provide substantial energy savings and contribute to the improvement of thermal comfort in buildings. For these systems, the ground temperature plays the main role. The present work aims to investigate numerically the influence of the nature of soil on the thermal behavior of the ground-to-air heat exchanger used for building passive cooling. We have taken into account in this work the influence of the soil nature by considering three types of dry soil: clay soil, sandy-clay soil and sandy soil. The mixed convection equations governing the heat transfers in the earth-to-air heat exchanger have been presented and discretized using the finite difference method with an Alternate Direction Implicit (ADI) scheme. The resulting algebraic equations are then solved using the algorithm of Thomas combined with an iterative Gauss-Seidel procedure. The results show that the flow is dominated by forced convection. The examination of the sensitivity of the model to the type of soil shows that the distributions of contours of streamlines, isotherms, isovalues of moisture are less affected by the variations of the nature of soil through the variation of the diffusivity of the soil. However, it is observed that the temperature values obtained for the clay soil are higher while the sandy soil shows lower temperature values. The values of the ground-to-air heat exchanger efficiency are only slightly influenced by the nature of the soil. Nevertheless, we note a slightly better efficiency for the sandy soil than for the sandy-clayey silt and clayey soils. This result shows that a sandy soil would be more suitable for geothermal system installations.