Development of a Multi-Agent-Based Simulation System
for Air Quality Analysis
Elia Georgiana DRAGOMIR
Petroleum-Gas University of Ploiesti
39, Bucharest Blvd, Ploiesti, 100680, Romania
Abstract: The implementation of distributed collaborative intelligence can improve the efficiency of agent-based environmental systems (for environmental networks) in the context of solving emergency situations in real time, such as the critical situation of severe air pollution with an important impact in a given region. In this paper it is presented a distributed multi-agent system for air quality monitoring and analysis (AQDMAS) whose first version was implemented in Zeus, a Java-based toolkit for intelligent agents’ development. The study is focused on the possibilities of the computer network distribution of the software agents. The purpose of the system is to verify the air quality standard fulfilment, and if, in case some exceedances occur, to inform the supervisor in order to take a decision. For this version there were designed seven intelligent agents placed in a local computer network in the Petroleum-Gas University of Ploiesti campus in Romania. The results revealed the effectiveness of the proposed monitoring and analyzing technique and the possibility of autonomous built-in simulation of tracking the air quality evolution with distributed resources.
Keywords: distributed multi agent system, air quality index, environment pollution, BDI logic.
CITE THIS PAPER AS:
Elia Georgiana DRAGOMIR, Development of a Multi-Agent-Based Simulation System for Air Quality Analysis, Studies in Informatics and Control, ISSN 1220-1766, vol. 23 (4), pp. 371-380, 2014. https://doi.org/10.24846/v23i4y201407
Air quality monitoring and analysis has become a very important environmental management activity in all European countries. Therefore most countries developed or have under development a national network of sites that monitor the concentrations of various air pollutants, depending on the local air pollution sources. In Romania, there is a National Network for Air Quality Monitoring that provides public measurements of some air pollutants in different locations. Thus a network is geographically distributed and can be modelled as a multi-agent system, each local station being viewed as an intelligent agent.
A brief review of the literature makes the evidence of the intensive research work already done in this domain. The monitoring and analysis of the environment problems is a domain where agent-based technology can provide proper solutions. Some research projects had reported in the literature the progress made in this direction , . The potential use of multi-agent systems in real time environmental monitoring, analysis, forecasting, and control raises new challenges for the researchers working in the area of distributed intelligent systems . Other applications of multi-agent systems in the environmental sciences have been reported in the literature: a self-organizing multi-agent system for simulating the processes responsible for the distribution of water availability over space and time in a semi-arid river basin , or for real time control of water distribution networks , and a multi-agent system for drinking water quality analysis from a distribution network .
Among these, the implementation of distributed collaborative intelligence can improve the efficiency of agent-based environmental systems (for environmental networks) in the context of solving emergency situations in real time, such as, for example, the critical situation of a severe air pollution with an important impact in a given region, amplified by specific meteorological conditions. An example is a hybrid multi agent system based on a reinforcement learning approach for real time air pollution monitoring presented in . The design of a two – level hierarchical multi agent system for the vehicle emission monitoring is modelled in Khoo and Meng . In  is presented a conceptual design of a multi agent wireless sensor actuator system for the indoor air pollution. In Roche et all  is designed a multi-agent gas turbine power plant systems and Chappin and Dijkema proposed an agent based model for the electricity production systems in order to explore the impact of CO2 emission-trading .
Our previous works in this research area include the references: Oprea et al. , a multi-agent system for dam monitoring, the AirQMAS presented in Oprea et al.  and the AgentAirPol System in Petre .
This paper presents a multi-agent based model of an intelligent system for air quality monitoring and analysis. As a case study a particular first version of the system it is implemented in Zeus, a Java-based toolkit for intelligent agents’ development . The preliminary experiments presented here are focused on the possibilities of the computer network distribution of the software agents.
One of the main objectives of this multi-agent system is to develop a BDI logic based model for a multi-agent system applied in the air quality monitoring domain. The model is design in order to reflect the geographical distributed characteristic, the real time system response and a high level of flexibility over the entire life-cycle: the system model is designed to adapt to most changes in the structure of the network, whether they are intentional (e.g., the addition of a sensor or stopping one for maintenance) or not (e.g., after an outage).
Multi-agent systems (MASs) enable this flexibility due to their inherent characteristics.
The rest of the paper is divided as follows. Section 2 briefly presents the MAS area of research. Section 3 describes the design of the agent’s model, including its conceptual framework, implementation process and knowledge evaluation aspects. Section 4 presents a discussion based on the experimental results, and Section 5 concludes the paper and identifies directions for future research.
- CHAPPIN, E. J. L., G. P. J. DIJKEMA, An Agent based Model of the System of Electricity Production Systems: Exploring the Impact of CO2 Emission-trading, Proceedings of IEEE International Conference on System of Systems Engineering, IEEE, San Antonio, TX, USA, 2007, pp. 1-5.
- COLLINS, J., D. NDUMU, The Application Realisation Guide, The Zeus Agent Building Toolkit, Intelligent Systems Research Group, BT Labs, 1999.
- DENZINGER, J., H. KASINGER, B. BAUER, Decentralized Real-time Control of Water Distribution Networks using Self-organizing Multi-agent Systems, SASO, 2010, 2013 IEEE 7th International Conference on Self-Adaptive and Self-Organizing Systems, pp. 223-232.
- DRAGOMIR, E. G., M. OPREA, A Multi-Agent System for Power Plants Air Pollution Monitoring, Proceedings of 2nd IFAC Workshop Convergence of Information Technologies and Control Methods with Power Systems, 2013, pp. 97-102.
- FAGIN, R., J. HALPERN, Y. MOSES, M. VARDI, Reasoning about Knowledge, MIT Press, Cambridge, 1995, MA, USA.
- HUANG, W., X. ZHANG, J. WANG, Multi-agent System Computing and Simulation of Inter-basin Water Transfer, Intelligent Automation & Soft Computing, vol. 17(7), 2011, pp. 897-908.
- KEPLICZ, B. D., R. VERBRUGGE, Teamwork in Multiagent Systems – A Formal Approach, John Wiley& Sons LTD, 2010.
- KHOO, H. K., Q. MENG, Modeling of Vehicle Emission Pricing Strategy Using Multi-agent System, Journal of the Eastern Asia Society for Transportation Studies, Vol. 8, 2010, pp. 883-895.
- MEYER, J.-J. C., W. VAN DER HOEK, Epistemic Logic for AI and Theoretical Computer Science, Cambridge University Press, 1995, Cambridge, UK.
- MENG, A., L. YE, D. ROY, P. PADILLA, Genetic Algorithm based Multi-agent System Applied to Test Generation, Computers and Education, vol. 49(4), 2007, pp. 1205-1223, ISSN 0360-1315.
- MORLEY, D., C. S. PARKER, J. LAVINE, Understanding Computers: Today and Tomorrow, 10th edition, Thomson Course Technology, 2004.
- NI, J., L. REN, M. LIU, D. ZHU, A Multiagent Dynamic Assessment Approach for Water Quality based on Improved q-Learning Algorithm, Mathematical Problems in Engineering, vol. 2013, Article ID 812032, 2013, 7 pages, doi:10.1155/2013/812032.
- OPREA, M., C. NICHITA, On the Distributed Water Pollution Control Solving with an Agent-Based Approach, Studies in Computational Intelligence, Springer, 2008, pp. 289-294.
- OPREA, M., A. MATEI, E. PETRE, Agent-based Modeling of a Dam Monitoring System, Proceedings of CSCS17, vol. 2, 2009, pp. 509-514.
- OPREA, M., M. CARBUREANU, E. G. DRAGOMIR, AirQMAS: A Collaborative Multi-agent System for Air Quality Analysis, Annals of the University of Craiova, series Automation, Computers, Electronics and Mechatronics, vol. 9(37), No 1, 2012.
- PAPALEONIDAS, A., L. ILIADIS, Hybrid and Reinforcement Multi agent Technology for Real time Air Pollution Monitoring, 8th IFIP WG 12.5 International Conference, AIAI 2012, Halkidiki, Greece, 2012, pp. 274-284.
- PETRE, E., AgentAirPol System, an Agent-based System for Air Pollution Analysis, Bulletin of PG University of Ploiesti, Series Mathematics, Informatics, Physics, vol. LX, nr. 1, 2008, pp. 63-72.
- RALHA, C. G., C. V. S. SILVA, A Multi-agent Data Mining System for Cartel Detection in Brazilian Government Procurement, Expert Systems with Applications, vol. 39, 2012, pp. 11642-11656.
- Reţeaua Naţională de Monitorizare a Calităţii Aerului, www.calitateaer.ro
- ROCHE, R., L. IDOUMGHAR, S. SURYANARAYANAN, M. DAGGAG, C. A. SOLACOLU, A. MIRAOUI, A Flexible and Efficient Multi-agent Gas Turbine Power Plant Energy Management System with Economic and Environmental Constraints, Applied Energy, vol. 101, 2013, pp. 644-654.
- VAN OEL, P. R., M. S. KROL, A. Y. ARJEN, Y. HOEKSTRA, R. R. TADDEI, Feedback Mechanisms between Water Availability and Water Use in a Semi-arid River Basin: A Spatially Explicit Multi-agent Simulation Approach, Environmental Modelling & Software, vol. 25, no. 4, 2010, pp. 433-443.
- WEISS, G., Multi-agent Systems – A Modern Approach to Distributed Artificial Intelligence, The MIT Press, Cambridge, 1999.
- WOOLDRIDGE, M., An Introduction to Multi-agent Systems (2nd ed.), Wiley Publishing, 2009, ISBN 0470519460, 9780470519462.
- WU, S., P. NOY, A Conceptual Design of a Wireless Sensor Actuator System for Optimizing Energy and Well-being in Buildings, Intelligent Buildings International, 2(1), 2010, pp. 41-56.