Grant: Collaborative Research and Development Grants
Simon Fraser University
$18,182.00
Statistical approaches for cleaning BCTC load data
EF 2010-11
Résumé
Load data refers to the power consumption recorded by meters at certain time intervals at the delivery point level. Load data is one of the most critical data for operation, planning and maintenance power systems, and contains vital information for day-to-day conditions, for evaluating system reliability performance indices, for energy saving, and for system planning and expansion. However, collecting all load data accurately in fine granularity is a challenging and costly task. For many years, British Columbia Transmission Corporation (BCTC) has been trying to address this issue of load data quality. Detecting corrupted or other invalid data is not an easy task because load data is naturally random due to uncertainty in the power consumption behaviors, outage events and dynamism of customers. The difficulty is compounded by the requirement of preserving the original patterns in the load data while removing invalid data and noises, instead of artificially making up the missed or corrupted data.
At present, BCTC is using simple rules and heuristics (such as cut-off values based on context specific knowledge and experiences) to fill up missing data or replace corrupted data. Although this process works in some cases, it requires much manual intervention and lacks a statistical guarantee on the validity of this operation. Most heuristics are context specific and cannot be applied to other application domains with a similar problem. It will be of great value to have a systematic and principled solution to this problem. The terms ""systematic"" and ""principled"" mean that the solution is based on well studied methodologies, such as statistical theory and data mining techniques, and is based on general assumptions about data distributions. For this purpose, the SFU's data mining group joins venture with BCTC to find a systematic and principled solution to cleaning the load data at BCTC. The knowledge and principles gained from such solutions should be also applicable to similar problems in other application domains as well.
Programme
Collaborative Research and Development Grants
Bénéficiaire
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
385373-2009
Name nom
Wang, Ke
Department département
Computing Science
Organization id
5
Institution établissement
Simon Fraser University
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2010
Competition year année de concours
2009
Award amount
18182
Program id
CRDPJ
Program name en
Collaborative Research and Development Grants
Program name fr
Subventions de recherche et développement coopérative
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
300
Area of application group en
Energy resources
Area of application group fr
Ressources d'énergie
Area of application en
Energy resources (including production, exploration, processing, distribution and use)
Area of application fr
Ressources d'énergie (production, exploration, traitement, distribution et utilisation de l'énergie)
Research subject code
2700
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Information technology
Research subject fr
Technologie de l'information
Partie
2
Nb partie
2
Application title
Statistical approaches for cleaning BCTC load data
Keyword
NSERC
Application summary
Load data refers to the power consumption recorded by meters at certain time intervals at the delivery point level. Load data is one of the most critical data for operation, planning and maintenance power systems, and contains vital information for day-to-day conditions, for evaluating system reliability performance indices, for energy saving, and for system planning and expansion. However, collecting all load data accurately in fine granularity is a challenging and costly task. For many years, British Columbia Transmission Corporation (BCTC) has been trying to address this issue of load data quality. Detecting corrupted or other invalid data is not an easy task because load data is naturally random due to uncertainty in the power consumption behaviors, outage events and dynamism of customers. The difficulty is compounded by the requirement of preserving the original patterns in the load data while removing invalid data and noises, instead of artificially making up the missed or corrupted data.
At present, BCTC is using simple rules and heuristics (such as cut-off values based on context specific knowledge and experiences) to fill up missing data or replace corrupted data. Although this process works in some cases, it requires much manual intervention and lacks a statistical guarantee on the validity of this operation. Most heuristics are context specific and cannot be applied to other application domains with a similar problem. It will be of great value to have a systematic and principled solution to this problem. The terms ""systematic"" and ""principled"" mean that the solution is based on well studied methodologies, such as statistical theory and data mining techniques, and is based on general assumptions about data distributions. For this purpose, the SFU's data mining group joins venture with BCTC to find a systematic and principled solution to cleaning the load data at BCTC. The knowledge and principles gained from such solutions should be also applicable to similar problems in other application domains as well.