Grant: Engage Grants Program
University of British Columbia
$23,000.00
Smart Grid data analytics for demand load forecasting
EF 2011-12
Résumé
The rapidly increasing deployment of smart grids world-wide is creating a phenomenon known in the industry
as a ""data tsunami:"" substantial amount of new information is being generated by the smart grid. Transforming
this data into actionable intelligence for utilities requires the development of new and innovative data analytic
algorithms. Utilities benefit significantly from smart grid analytics by optimizing their generation, transmission
and distribution. According to a market intelligence report by Pike Research, the cleantech industry is expected
to invest over $11B on the development of smart-grid analytics, from 2011 to 2015.
The purpose of this work is to develop an innovative algorithm to perform short-term load demand forecasting
with increased accuracy. Currently utilities predict load demand by observing the total (i.e. aggregate)
consumption of a region over time, and modeling the response to a limited set of variables such as weather and
time. Due to lack of granularity in data, the traditional methods perform consumption modeling using
""black-box"" systems in which no knowledge of the internal components can be utilized. In other words,
black-box modeling only explores the response of output signals to the change in input variables.
Using the depth of information available through smart grids, consumer behavior can be accurately modeled,
and as a result, ""white-box"" forecast algorithms (e.g., statistical methods) can be applied which utilize the
knowledge of the inner workings of the system to enhance the modeling accuracy. As a result of this work,
more accurate load demand forecasting for the immediate 24 to 72 hours can be achieved. This creates millions
of dollars of annual savings for utilities by allowing them to make more informed decisions regarding power
generation, distribution, and trading.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
429371-2011
Name nom
Wang, Jane
Department département
Electrical and Computer Engineering
Organization id
2
Institution établissement
University of British Columbia
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2011
Competition year année de concours
2011
Award amount
23000
Program id
EGP
Program nane en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1554
Committee name en
Pacific Internal Decision Committee
Committee name fr
Comité de décision interne pour le Pacifique
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
2713
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Algorithms
Research subject fr
Algorithmes
Partie
1
Nb partie
1
Application title
Smart Grid data analytics for demand load forecasting
Keyword
NSERC
Application summary
The rapidly increasing deployment of smart grids world-wide is creating a phenomenon known in the industry
as a ""data tsunami:"" substantial amount of new information is being generated by the smart grid. Transforming
this data into actionable intelligence for utilities requires the development of new and innovative data analytic
algorithms. Utilities benefit significantly from smart grid analytics by optimizing their generation, transmission
and distribution. According to a market intelligence report by Pike Research, the cleantech industry is expected
to invest over $11B on the development of smart-grid analytics, from 2011 to 2015.
The purpose of this work is to develop an innovative algorithm to perform short-term load demand forecasting
with increased accuracy. Currently utilities predict load demand by observing the total (i.e. aggregate)
consumption of a region over time, and modeling the response to a limited set of variables such as weather and
time. Due to lack of granularity in data, the traditional methods perform consumption modeling using
""black-box"" systems in which no knowledge of the internal components can be utilized. In other words,
black-box modeling only explores the response of output signals to the change in input variables.
Using the depth of information available through smart grids, consumer behavior can be accurately modeled,
and as a result, ""white-box"" forecast algorithms (e.g., statistical methods) can be applied which utilize the
knowledge of the inner workings of the system to enhance the modeling accuracy. As a result of this work,
more accurate load demand forecasting for the immediate 24 to 72 hours can be achieved. This creates millions
of dollars of annual savings for utilities by allowing them to make more informed decisions regarding power
generation, distribution, and trading.