Estimating appliance-level energy consumption in residential buildings using graphical methods on whole house power measurements

piloturuguayanΤεχνίτη Νοημοσύνη και Ρομποτική

15 Οκτ 2013 (πριν από 3 χρόνια και 8 μήνες)

73 εμφανίσεις

Estimating appliance
-
level energy consumption

in residential buildings

using
graphical methods

on whole house power measurements


Suman Giri, Mario Bergés

(
sgiri@andrew.cmu.edu
, mberges@andrew.cmu.edu)


Department of Civil and Environmental Engineering,

Carnegie Mellon University, Pittsburgh PA 15217



One way to promote energy efficient behavior

among consumers
is to provide
them feedback in the form of

appliance
-
level breakdown of
their
total energy c
onsumption, which is achievable through methods now
known as non
-
intrusive load monitoring (NILM)

[1
]
.
A typical NILM system collects overall voltage
and/or current measurements for a home at a limited number of locations in the power distribution system,
and uses machine learning and signal processing techniques to infer the behavior of individual appliances
from these aggregate measurements, and provides an estimate of their energy consumption.

This
type of
appliance
-
level energy feedback
has

been

shown t
o r
esult in savings of up to 12% [2
].


In the past 20 years considerable advances have been made in the NILM domain
(a good review can be
found in
[
3
]
),

but a complete and feasible solution
still
eludes the mainstream market.
R
ecent research
interest

in t
his field

has been towards using algorithms that learn based on unsupervised methods [
4,5&6
].
The use of algorithms like Hidden Markov Models (HMMs) and its derivatives including efficient
inference algorithms have been proposed, but a thorough test of the

efficacy of these methods on real life
data has yet to be carried out.


Although there exist a limited number of publicly available datasets of voltage and current measurements
for homes (e.g., REDD [
7
])
, the lack of labels for events
(i.e., appliance st
ate transitions)
make it difficult
for researchers to test their event
-
based algorithms on them, and these datasets sometimes do not include
appliance
-
level energy breakdown resulting in ambiguities

in
the accuracy
measures
reported b
y
researchers
. Recentl
y, another dataset


BLUED has been released [
8
] which provides detailed labels of
events including individual power consumptions of all monitored devices. In this paper, we test
NILM
approaches based on graphical models [
4 & 5
], using

the BLUED dataset to

observe the actual level of
accuracy and device granularity achievable through these means.
I
n doing so, we aim to make a conclusive
statement about the practicality of using probability based methods as opposed to event
-
based methods as a
solution for NI
LM problems.



References


[1] G. Hart, “Nonintrusive appliance load monitoring,”
Proceedings of the IEEE, vol. 80, no. 12, pp. 1870

1891,

Aug. 2002.



[2] K. Ehrhardt
-
Martinez, K. Donnelly, J. A. “Skip” Laitner, D. York, J. Talbot, and K. Friedrich,
“Advanced Metering Initiatives and Residential Feedback Programs: A Meta
-
Review for Economy
-
wide
Electricity Savings.” American Council for an Energy
-
Efficient Economy, Washington, D.C., E105, Jun.
2010.


[3] M. Zeifman and K. Roth, “Nonintrusive appliance

load monitoring: Review and outlook,” in 2011 IEEE
International Conference on Consumer Electronics (ICCE), 2011, pp. 239

240.


[4]

H. Kim, M. Marwah, M. Arlitt, G. Lyon, and J. Han. “Unsupervised disaggregation of low frequency
power measurements”. In
Proceedings of the SIAM Conference on Data Mining, 2011.


[5] J. Z. Kolter and T. Jaakkola
. Approximate Inference in Additive Factorial HMMs with Application to
Energy Disaggregation. In International Conference on Artificial Intelligence and Statistics, pages 1472
-
1482, LaPalma, Canary Islands, 2012.


[6] Parson O, Ghosh S, Weal M, Rogers A. N
on
-
intrusive Load Monitoring using Prior Models of General
Appliance Types. In: 26th AAAI Conference on Artificial Intelligence. Toronto, Canada. 2012.


[7] Zico Kolter and Matthew J. Johnson. REDD: A public data set for energy disaggregation research. In
proceedings of the SustKDD workshop on Data Mining Applications in Sustainability, 2011.


[8] K. Anderson, A. Ocneanu, D. Benitez, D. Carlson, A. Rowe, and M. Berges, "BLUED: A Fully Labeled
Public Dataset for Event
-
Based Non
-
Intrusive Load Monitoring Rese
arch," in Proceedings of the 2nd KDD
Workshop on Data Mining Applications in Sustainability (SustKDD), Beijing, China.