Fog Computing is an emerging paradigm that distributes computing and networking services closer to where user data is generated. The Fog presents a new architecture that “takes processing to the data”. The fog will resolve in the Internet of Things such as bandwidth and cost constraints and performing data fusion, etc. Considering the “distributed” property, this paper proposes to exploit the multi agent system technology for the development of the fog system. To demonstrate its feasibility, we adopt an open source platform for a multi agent system, VOLTTRON. Then, four types of fog agents are developed that collaborate to conduct building energy management tasks in an autonomous manner. The agents can reduce the energy waste in a building by managing the brightness of lights, power status of the HVAC systems, and various energy loads. They also receive weather data and price data from Korea Meteorological Administration and Korea Power Exchange and present the data on the web. This helps user to recognize the information easier.
[1]
Nicholas R. Jennings,et al.
Intelligent agents: theory and practice
,
1995,
The Knowledge Engineering Review.
[2]
Gerhard Weiss,et al.
Multi-Agent Systems
,
2013
.
[3]
Hyacinth S. Nwana,et al.
ZEUS: a toolkit and approach for building distributed multi-agent systems
,
1999,
AGENTS '99.
[4]
Agostino Poggi,et al.
JADE: a FIPA2000 compliant agent development environment
,
2001,
AGENTS '01.
[5]
Lingfeng Wang,et al.
Multi-agent based energy and comfort management in a building environment considering behaviors of occupants
,
2012,
PES 2012.
[6]
Paulo F. Ribeiro,et al.
Multi-agent system architecture for smart home energy management and optimization
,
2013,
IEEE PES ISGT Europe 2013.
[7]
Jereme Haack,et al.
VOLTTRON: An Agent Execution Platform for the Electric Power System
,
2012
.