Journal article
Modelling the weekly electricity consumption of small to medium enterprises
- Abstract:
- Electricity consumption will evolve as more low carbon technology is adopted. To continue supplying electricity reliably into the future, Distribution Network Operators (DNOs) need to better understand low voltage customers. This can be gained from smart meter data, but DNOs may have limited access. We demonstrate a method to create an energy demand profile for a small to medium enterprise (SME) without a smart meter based only on operational hours, mean daily use (from quarterly readings), and smart meter data from other SMEs. We cluster the smart meter data using a simple Gaussian mixture model, thereby providing five groups of customers easily identified by their mean daily use. A new meter is assigned a cluster and an electricity profile created. For comparison, a profile is also created when the smart meter data is not clustered. The average difference between the actual and predicted operational/non-operational power is less than 0.2kWh, and clustering reduces the range around this difference. The methods presented here out perform the flat profile (akin to current methods). Additionally, we found no relationship between electricity consumption and non-energy traits such as type of business and number of employees; and SMEs electricity consumption is not significantly affected by weather.
- Publication status:
- Submitted
- Peer review status:
- Under review
Actions
Authors
- Publication date:
- 2014-07-01
- Edition:
- Author's Original
- Language:
-
English
- Keywords:
- Subjects:
- UUID:
-
uuid:1f2e4169-4da7-4f08-ace7-87ac4f945e73
- Local pid:
-
ora:8827
- Deposit date:
-
2014-07-22
Terms of use
- Copyright holder:
- Tamsin E Lee et al
- Copyright date:
- 2014
If you are the owner of this record, you can report an update to it here: Report update to this record