Header

UZH-Logo

Maintenance Infos

Adaptive home heating under weather and price uncertainty using GPs and MDPs


Shann, Michael; Seuken, Sven (2014). Adaptive home heating under weather and price uncertainty using GPs and MDPs. In: International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Paris, France, 5 May 2014 - 9 May 2014.

Abstract

We consider the problem of adaptive home heating in the smart grid, assuming that real-time electricity prices are being exposed to end-users with the goal of realizing demand-side management. To lower the burden on the end-users, our goal is the design of a smart thermostat that automatically heats the home, optimally trading o the user’s comfort and cost. This is a challenging problem due to two sources of uncertainty: future weather conditions and future electricity prices. Our main technical contribution is a general technique that uses predictive distributions obtained from Gaussian Process (GP) regressions to compute the state transition probabilities of an MDP, such that the solution to the resulting MDP constitutes a sequentially optimal policy. We apply this general approach to the home-heating problem, where we use the predictive distributions of the GPs for the day-ahead external temperatures and electricity prices. The solution to the home-heating MDP constitutes an optimal heating policy that maximizes the user’s utility given the probability information gathered by the Gaussian process model. Via simulations we show that our MDP-based approach outperforms various benchmarks, especially for cost-sensitive users.

Abstract

We consider the problem of adaptive home heating in the smart grid, assuming that real-time electricity prices are being exposed to end-users with the goal of realizing demand-side management. To lower the burden on the end-users, our goal is the design of a smart thermostat that automatically heats the home, optimally trading o the user’s comfort and cost. This is a challenging problem due to two sources of uncertainty: future weather conditions and future electricity prices. Our main technical contribution is a general technique that uses predictive distributions obtained from Gaussian Process (GP) regressions to compute the state transition probabilities of an MDP, such that the solution to the resulting MDP constitutes a sequentially optimal policy. We apply this general approach to the home-heating problem, where we use the predictive distributions of the GPs for the day-ahead external temperatures and electricity prices. The solution to the home-heating MDP constitutes an optimal heating policy that maximizes the user’s utility given the probability information gathered by the Gaussian process model. Via simulations we show that our MDP-based approach outperforms various benchmarks, especially for cost-sensitive users.

Statistics

Citations

Altmetrics

Downloads

1 download since deposited on 27 Oct 2014
0 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Language:English
Event End Date:9 May 2014
Deposited On:27 Oct 2014 16:48
Last Modified:21 Aug 2017 00:09
Publisher:ACM
ISBN:978-1-4503-2738-1
Related URLs:http://www.ifaamas.org/Proceedings/aamas2014/starthere.htm
Other Identification Number:merlin-id:10436

Download

Preview Icon on Download
Filetype: PDF - Registered users only
Size: 663kB