Artificial Decision Making Under Uncertainty in Intelligent Buildings

TL;DR

This paper demonstrates that automated decision support in multi-agent intelligent building systems can enhance energy efficiency and user experience by enabling agents to make effective decisions under uncertainty and real-time constraints.

Contribution

It introduces methods for agents to make bounded rational decisions under uncertainty in dynamic, real-time environments, relaxing previous assumptions.

Findings

Agents can make effective decisions despite uncertainties.

Decision support improves energy savings and user experience.

Methods generalize to other domains with real-time constraints.

Abstract

Our hypothesis is that by equipping certain agents in a multi-agent system controlling an intelligent building with automated decision support, two important factors will be increased. The first is energy saving in the building. The second is customer value---how the people in the building experience the effects of the actions of the agents. We give evidence for the truth of this hypothesis through experimental findings related to tools for artificial decision making. A number of assumptions related to agent control, through monitoring and delegation of tasks to other kinds of agents, of rooms at a test site are relaxed. Each assumption controls at least one uncertainty that complicates considerably the procedures for selecting actions part of each such agent. We show that in realistic decision situations, room-controlling agents can make bounded rational decisions even under dynamic real-time constraints. This result can be, and has been, generalized to other domains with even harsher time constraints.