[论文解读] A Multi-Agent based Approach for Simulating the Impact of Human Behaviours on Air Pollution

Sabri Ghazi, Julie Dugdale+1 more|arXiv (Cornell University)|Apr 8, 2019

Transportation Planning and Optimization被引用 7

一句话总结

本文提出一种多智能体系统（MAS），通过演化N人囚徒困境博弈，模拟人为工业排放决策对空气污染的影响，其中智能体根据实时污染水平和气象数据调整排放速率。该模型结合烟羽扩散模型与人工神经网络（ANN），用于预测污染浓度，结果表明监管处罚能增强智能体间的合作，改善空气质量控制。

ABSTRACT

This paper presents a Multi-Agent System (MAS) approach for designing an air pollution simulator. The aim is to simulate the concentration of air pollutants emitted from sources (e.g. factories) and to investigate the emergence of cooperation between the emission source managers and the impact this has on air quality. The emission sources are controlled by agents. The agents try to achieve their goals (i.e. increase production, which has the side effect of raising air pollution) and also cooperate with others agents by altering their emission rate according to the air quality. The agents play an adapted version of the evolutionary N-Person Prisoners' Dilemma game in a non-deterministic environment; they have two decisions: decrease or increase the emission. The rewards/penalties are influenced by the pollutant concentration which is, in turn, determined using climatic parameters. In order to give predictions about the Plume Dispersion) model and an ANN (Artificial Neural Network) prediction model. The prediction is calculated using the dispersal information and real data about climatic parameters (wind speed, humidity, temperature and rainfall). Every agent cooperates with its neighbours that emit the same pollutant, and it learns how to adapt its strategy to gain more reward. When the pollution level exceeds the maximum allowed level, agents are penalised according to their participation. The system has been tested using real data from the region of Annaba (North-East Algeria). It helped to investigate how the regulations enhance the cooperation and may help controlling the air quality. The designed system helps the environmental agencies to assess their air pollution controlling policies.

研究动机与目标

• 通过基于智能体的仿真，建模工业排放决策与空气质量之间的动态相互作用。
• 研究在监管压力下，排放源管理者之间合作如何产生。
• 开发一个整合真实气象数据与污染扩散建模的预测仿真框架。
• 评估环境法规通过智能体激励机制促进减排的有效性。
• 支持环境机构利用仿真结果评估和优化空气质量控制政策。

提出的方法

• 智能体代表工业排放源，根据奖励与惩罚机制决定增加或减少排放。
• 智能体在非确定性环境中参与一种改进的演化N人囚徒困境博弈。
• 利用烟羽扩散模型结合真实气象参数（风速、湿度、温度、降雨量）预测污染浓度。
• 使用真实数据训练人工神经网络（ANN），以提升污染浓度预测的准确性。
• 智能体与排放相同污染物的邻近智能体合作，并根据集体污染水平调整策略。
• 当污染超过监管阈值时施加处罚，以激励减排与合作。

实验结果

研究问题

• RQ1 在模拟的污染环境中，监管处罚下智能体的排放决策如何演变？
• RQ2 当污染水平被监测并施加处罚时，排放智能体之间的合作在多大程度上得以产生？
• RQ3 结合烟羽扩散模型与ANN的模型在多大程度上能准确预测实时空气污染浓度？
• RQ4 气象参数在塑造污染扩散的时空动态中发挥何种作用？
• RQ5 监管处罚在促进长期减排与改善空气质量方面有多有效？

主要发现

• 当污染超过监管阈值时，该模型成功模拟出排放智能体之间合作的出现。
• 监管处罚显著降低了总体排放水平，通过激励智能体集体减少排放。
• 将烟羽扩散模型与ANN结合，相比独立模型，显著提高了污染浓度预测的准确性。
• 风速与降雨量等气象参数被发现对污染扩散模式具有显著影响。
• 仿真结果表明，环境机构可利用该模型评估与优化空气质量控制政策。
• 智能体随时间调整其策略，表现出对污染水平与处罚变化的学习行为。