Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Engage Grants Program

École de technologie supérieure

$25,000.00

Forecasting multiple-correlated waste collecting sites

EF 2016-17

Résumé
Valuable waste collection as well as other reverse logistic operations are increasingly important for severalsmall businesses. They are similar to residential municipal services, such as garbage and recycling collectionsand public safety service provisions (e.g. firefighters, ambulances, emergency vehicles, police, dangerousmaterial disposal units, etc.).Waste generation is quasirandom in nature and is geographically distributed. The generation is correlated todemography, economic welfare, population commutes, especial events, short-term periods (e.g. holidays andfestivities), trend and seasonality. Most of the collections consist of picking operations subject to the capacityof adapted vehicles and on-site facilities. To plan waste collection operations, it is important to have reliableinformation from the sites.Usually, companies carrying these operations must solve complex Vehicle Routing Problems (VRP) with fleetlimitations, which introduces other sources of randomness. Moreover, client time windows add morecomplexity to the VR process. Long collection delays are unacceptable and companies are penalized becausewaste becomes a safety hazard. As the market for valuable waste grows, competition also increases as well astheft operations and vandalism. Excessive sampling is also penalized as it distracts small businesses of theirduties and increases costs. Corrective actions affect VR previous decisions and force last minutes changes.Even worst, it could end in real-time decisions with increasing costs.We propose to model this problem by associating similar clients (in terms of business, size, past production,geographical zones, collections frequency and stock capacity, etc.), assuming discrete journal contributions andusing Singular Value Decomposition (SVD) and K-clustering. Then, using few representative clients byclusters (e.g. those collected in the past days) it would be possible to forecast the rest of the cluster for everyday in a short-term horizon. We also propose to associate similar clients in terms of geographic zones and
Programme
Engage Grants Program
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
499363-2016
Name nom
Ouhimmou, Mustapha
Department département
Génie de la production automatisée
Organization id
53
Institution établissement
École de technologie supérieure
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2016
Competition year année de concours
2016
Award amount
25000
Program id
EGP
Program name 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
1552
Committee name en
Quebec Internal Decision Committee
Committee name fr
Comité de décision interne pour le Québec
Area of application code
520
Area of application group en
Manufacturing processes and products
Area of application group fr
Procédés et produits industriels
Area of application en
Production and operations management
Area of application fr
Production et gestion des opérations
Research subject code
1603
Research subject group en
Industrial engineering
Research subject group fr
Génie industriel
Research subject en
Logistics
Research subject fr
Logistique
Partie
1
Nb partie
1
Application title
Forecasting multiple-correlated waste collecting sites
Keyword
NSERC
Application summary
Valuable waste collection as well as other reverse logistic operations are increasingly important for severalsmall businesses. They are similar to residential municipal services, such as garbage and recycling collectionsand public safety service provisions (e.g. firefighters, ambulances, emergency vehicles, police, dangerousmaterial disposal units, etc.).Waste generation is quasirandom in nature and is geographically distributed. The generation is correlated todemography, economic welfare, population commutes, especial events, short-term periods (e.g. holidays andfestivities), trend and seasonality. Most of the collections consist of picking operations subject to the capacityof adapted vehicles and on-site facilities. To plan waste collection operations, it is important to have reliableinformation from the sites.Usually, companies carrying these operations must solve complex Vehicle Routing Problems (VRP) with fleetlimitations, which introduces other sources of randomness. Moreover, client time windows add morecomplexity to the VR process. Long collection delays are unacceptable and companies are penalized becausewaste becomes a safety hazard. As the market for valuable waste grows, competition also increases as well astheft operations and vandalism. Excessive sampling is also penalized as it distracts small businesses of theirduties and increases costs. Corrective actions affect VR previous decisions and force last minutes changes.Even worst, it could end in real-time decisions with increasing costs.We propose to model this problem by associating similar clients (in terms of business, size, past production,geographical zones, collections frequency and stock capacity, etc.), assuming discrete journal contributions andusing Singular Value Decomposition (SVD) and K-clustering. Then, using few representative clients byclusters (e.g. those collected in the past days) it would be possible to forecast the rest of the cluster for everyday in a short-term horizon. We also propose to associate similar clients in terms of geographic zones and