Reconfigurable manufacturing systems have been proposed over the last decades to deal with mass-customization problems and volatile markets. The results comparison shows that the proposed optimised empty container repositioning framework can significantly reduce the shipping line’s costs and make full use of empty containers. The model was applied to the Asia–Middle East region to simulate global empty containers repositioning in the region. Using simulated annealing (SA), shipping line agents were able to optimise empty container repositioning to determine the best sequence for moving containers. In the system, ports, shipping companies, customers, and empty containers were identified as critical agents. An agent-based maritime logistic empty container redistribution model was developed to help minimize the total relevant costs for empty container movement in the planning horizon. This research proposes a Maritime Empty Container Reposition Modelling Framework by integrating the agent-based modelling (ABM) paradigm to model the global movements of empty containers. Empty containers accumulated at specific ports cannot only generate profit but also increase the environmental footprint. In addition, wediscuss challenges in simulating 100 million agents.ĭue to an ever-increasing movement of containers across the globe in line with the economic boom, the trade imbalance and issues related to empty containers have become inevitable. We demonstrate performanceimprovement for Pune and Mumbai cities with 3.2 and 12 million populations respectively. In this paper, we share our ongoing journey of developing it as a highly scalable cloud readyparallel and distributed implementation to simulate up to 100 million agents. However,the current implementation is not scalable for this purpose, since it has a well-tuned serial implementationat its core. Our goal is to simulate larger citieslike Mumbai (with 12 million population) first, and then entire India with its 1+ billion population. We could demonstrate EpiRust scaling up to a few millions of agents, for example a COVID-19 infection spreading through Pune city with its 3.2 million population. It has been developed with three key factors in mind namely 1. The experiments and analyses demonstrate that the Agents can mitigate CRA in a distributed way to mitigate the associated risks while achieving acceptable load balancing performance.ĮpiRust is an open source, large-scale agent-based epidemiological simulation framework developed usingRust language. The Agent’s policies include the following: (i) a heuristic migration optimization policy to select the VMs to be migrated and the matching hosts (ii) a migration trigger policy to determine whether the host needs to relocate the VMs (iii) an acceptance policy to decide if the migration request should be accepted and (iv) a balancer heuristic policy to make the initial VM allocation. This paper presents an Agent-based VM migration solution that can balance the burden on commercially diverse servers and avoid potential co-resident attacks by utilizing VM live migrations. These two issues may cause uneven resource usage within the server and attacks on the service, leading to performance and security degradation. Additionally, co-located VMs are vulnerable to co-resident attacks (CRA) in a networked environment. The majority of cloud computing consists of servers with different configurations which host several virtual machines (VMs) with changing resource demands. This experimental environment can also be utilized to perform a wide range of intelligent algorithm experiments. The implementation makes use of various machine learning and deep learning algorithms as possible evaluation scenarios. To facilitate this, we have also provided a GitHub link for the project. In this work, we present the ongoing development and implementation of various network service agents utilizing the PADE framework. However, despite this progress, there remains a lack of suitable simulation environments for evaluating the performance of multi-agent systems within these softwarized networks. Recently, the introduction of a softwarized intelligent network architecture and design guidelines using agents as building blocks, has been proposed for the upcoming 6G networks. This, coupled with other benefits, has made the use of multi-agent-based intelligent network service design a popular and cutting-edge paradigm in the field of network research. The agent-based approach to service design offers a distinct advantage over traditional microservice-based design by providing not only reactive responses but also the ability to proactively anticipate and address potential issues.
0 Comments
Leave a Reply. |