Data from: Modeling the internet of things, self-organizing and other complex adaptive communication networks: a cognitive agent-based computing approach

Background: Computer Networks have a tendency to grow at an unprecedented scale. Modern networks involve not only computers but also a wide variety of other interconnected devices ranging from mobile phones to other household items fitted with sensors. This vision of the "Internet of Things" (IoT) implies an inherent difficulty in modeling problems. Purpose: It is practically impossible to implement and test all scenarios for large-scale and complex adaptive communication networks as part of Complex Adaptive Communication Networks and Environments (CACOONS). The goal of this study is to explore the use of Agent-based Modeling as part of the Cognitive Agent-based Computing (CABC) framework to model a Complex communication network problem. Method: We use Exploratory Agent-based Modeling (EABM), as part of the CABC framework, to develop an autonomous multi-agent architecture for managing carbon footprint in a corporate network. To evaluate the application of complexity in practical scenarios, we have also introduced a company-defined computer usage policy. Results: The conducted experiments demonstrated two important results: Primarily CABC-based modeling approach such as using Agent-based Modeling can be an effective approach to modeling complex problems in the domain of IoT. Secondly, the specific problem of managing the Carbon footprint can be solved using a multiagent system approach.

背景：计算机网络正以前所未有的规模持续扩张。现代网络所覆盖的对象已不限于计算机，还包含种类丰富的互联设备——从移动电话到搭载传感器的各类家用智能设备。这种‘物联网（Internet of Things, IoT）’的愿景，使得相关建模问题天然存在固有难度。目的：针对复杂自适应通信网络与环境（Complex Adaptive Communication Networks and Environments, CACOONS）范畴内的大规模复杂自适应通信网络，实际无法对其全部场景进行落地实现与测试验证。本研究旨在探索将智能体建模（Agent-based Modeling）应用于认知智能体计算（Cognitive Agent-based Computing, CABC）框架，以完成复杂通信网络问题的建模工作。方法：本研究依托CABC框架，采用探索式智能体建模（Exploratory Agent-based Modeling, EABM）方法，搭建了用于企业网络碳足迹管理的自主多智能体架构。为验证复杂建模方法在实际场景中的应用效果，本研究同时引入了企业自研的计算机使用规范。结果：本次实验得出两项核心结论：其一，基于CABC的建模方案（如智能体建模方法）可有效用于物联网领域复杂问题的建模；其二，多智能体系统方法可解决企业网络碳足迹管理这一特定问题。