Showing papers on "Contract Net Protocol published in 2021"

An Online Distributed Satellite Cooperative Observation Scheduling Algorithm Based on Multiagent Deep Reinforcement Learning

Abstract: The provision of real-time information services is one of the crucial functions of satellites. In comparison with the centralized scheduling, the distributed scheduling can provide better robustness and extendibility. However, the existing distributed satellite scheduling algorithms require a large amount of communication between satellites to coordinate tasks, which makes it difficult to support scheduling in real-time. This letter proposes a multiagent deep reinforcement learning (MADRL)-based method to solve the problem of scheduling real-time multisatellite cooperative observation. The method enables satellites to share their decision policy, but it is not necessary to share data on the decisions they make or data on their current internal state. The satellites can use the decision policy to infer the decisions of other satellites to decide whether to accept a task when they receive a new request for observations. In this way, our method can significantly reduce the communication overhead and improve the response time. The pillar of the architecture is a multiagent deep deterministic policy gradient network. Our simulation results show that the proposed method is stable and effective. In comparison with the Contract Net Protocol method, our algorithm can reduce the communication overhead and achieve better use of satellite resources.

An Intelligent Fleet Condition-Based Maintenance Decision Making Method Based on Multi-Agent

Abstract: According to the demand for condition-based maintenance online decision making among a mission oriented fleet, an intelligent maintenance decision making method based on Multi-agent and heuristic rules is proposed. The process of condition-based maintenance within an aircraft fleet (each containing one or more Line Replaceable Modules) based on multiple maintenance thresholds is analyzed. Then the process is abstracted into a Multi-Agent Model, a 2-layer model structure containing host negotiation and independent negotiation is established, and the heuristic rules applied to global and local maintenance decision making is proposed. Based on Contract Net Protocol and the heuristic rules, the maintenance decision making algorithm is put forward. Finally, a fleet consisting of 10 aircrafts on a 3-wave continuous mission is illustrated to verify this method. Simulation results indicate that this method can improve the availability of the fleet, meet mission demands, rationalize the utilization of support resources and provide support for online maintenance decision making among a mission oriented fleet.

Real-Time Task Allocation of Heterogeneous Unmanned Aerial Vehicles for Search and Prosecute Mission

Abstract: In recent years, the Internet of Things (IoT) has developed rapidly after the era of computers and smart phones, which is expected to be applied to cities to improve the quality of life and realize the intelligence of smart cities. In particular, with the outbreak of coronavirus disease 2019 (COVID-19) last year, in order to reduce contact, some IoT devices, such as robots, unmanned aerial vehicles (UAVs), and unmanned vehicles, have played a great role in temperature monitoring, goods delivery, and so on. In this paper, we study the real-time task allocation problem of heterogeneous UAVs searching and delivering goods in the city. Considering the resource requirement of task and resource constraints of the UAV, when the resource of a single UAV cannot meet the requirement of the task, we propose a method of forming a UAV coalition based on contract net protocol. We analyze the coalition formation problem from two aspects: mission completion time and UAV’s energy consumption. Firstly, the mathematical model is established according to the optimization objective and condition constraints. Then, according to the established mathematical model, different coalition formation algorithms are proposed. To minimize the mission completion time, we propose a two-stage coalition formation algorithm. Aiming at minimizing the UAV’s energy consumption, it is transformed into a zero-one integer programming problem, which can be solved by the existing solver. Then, considering both mission completion time and energy consumption, we propose a coalition formation algorithm based on a resource tree. Finally, we design some simulation experiments and compare with the task allocation algorithm based on resource welfare. The simulation results show that our proposed algorithms are feasible and effective.

Urban search and rescue (USAR) simulation system: spatial strategies for agent task allocation under uncertain conditions

Abstract: . Task allocation under uncertain conditions is a key problem for agents attempting to achieve harmony in disaster environments. This paper presents an agent-based simulation to investigate task allocation considering appropriate spatial strategies to manage uncertainty in urban search and rescue (USAR) operations. The proposed method is based on the contract net protocol (CNP) and implemented over five phases: ordering existing tasks considering intrinsic interval uncertainty, finding a coordinating agent, holding an auction, applying allocation strategies (four strategies), and implementing and observing the real environment. Applying allocation strategies is the main innovation of the method. The methodology was evaluated in Tehran's District 1 for 6.6, 6.9, and 7.2 magnitude earthquakes. The simulation began by calculating the numbers of injured individuals, which were 28 856, 73 195, and 111 463 people for each earthquake, respectively. Simulations were performed for each scenario for a variety of rescuers (1000, 1500, and 2000 rescuers). In comparison with the CNP, the standard duration of rescue operations with the proposed approach exhibited at least 13 % improvement, with a maximal improvement of 21 %. Interval uncertainty analysis and comparison of the proposed strategies showed that increased uncertainty led to increased rescue time for the CNP and strategies 1 to 4. The time increase was less with the uniform distribution strategy (strategy 4) than with the other strategies. The consideration of strategies in the task allocation process, especially spatial strategies, facilitated both optimization and increased flexibility of the allocation. It also improved conditions for fault tolerance and agent-based cooperation stability in the USAR simulation system.

Analysis of Factory Automated Guided Vehicles Systems Using Contract Net Protocol

Abstract: Automated Guided Vehicles (AGVs) are used in a flexible job shop production system. In this type of production system, proper scheduling of tasks is the most important issue. This issue is considered to be non-deterministic polynomial time-hard and difficult to solve in a reasonable time. Moreover, in the semiconductor manufacturing process, contamination by airborne debris and vibrations during transportation have a significant impact on the manufacturing yield because of the fine processing, so there are constraints that AGV in the factory must pass on a predetermined transportation route. This constraint causes spatial interference between AGVs, which results in congestion of AGV on the transfer task. In this paper, an analytical model is investigated by using the multi-agent system that takes into account the spatial interference model of the AGV. In addition, we applied the contract net protocol, treating the processing equipment as the task manager and the AGV as the contractor in dynamically negotiating the contract. Our analytical model in which the AGV assignment agent and the task manager agent collaborate make decisions using feedback of time-series information of traffic congestion. By using this approach, we found that traffic flow could be improved.

Management of Multi-agents in a Smart Grid Network with the Python Using the Contract Net Protocol

Abstract: Smart grids are one of the best solutions for the integration of different distributed energy sources (DES), load, and storage elements. However, optimizing and managing these systems is a big challenge because it is only done in a distributed way. One of the best methods of managing a smart grid is the use of artificial intelligence (AI), especially multi-agent systems (MAS) approaches. This work constitutes a demonstration of one of those methods which is the contract net protocol (CNP). We will use the extended version of the contract net protocol(ECNP) to optimize the movement of MASs inside a smart grid network. Our example of a smart grid will be a grid constituted from nodes, and each node is a location of an element of the smart grid which could be a wind turbine, a customer…, in other words, a task or/and an agent. In the scenario each task it’s given a target which is also a node inside the grid, and our main objective is that the agent or agents could contribute to each task, depending on their priority order and may allow it to reach its target, which is another node in the network far from its initial location, using the shortest way as possible.