Publications:Large-scale monitoring of operationally diverse district heating substations : A reference-group based approach

From ISLAB/CAISR

Do not edit this section

Keep all hand-made modifications below

Title Large-scale monitoring of operationally diverse district heating substations : A reference-group based approach
Author Shiraz Farouq and Stefan Byttner and Mohamed-Rafik Bouguelia and Natasa Nord and Henrik Gadd
Year 2019
PublicationType Journal Paper
Journal Engineering applications of artificial intelligence
HostPublication
Conference
DOI
Diva url http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:1370681
Abstract A well-understood prior model for a District Heating (DH) substation is rarely available. Alternatively, since DH substations in a network share a common task, one can assume that they are all operationally homogeneous. Any DH substation that does not conform with the majority is an outlier, and therefore ought to be investigated. However, a DH substation can be affected by varying social and technical factors. Such details are rarely available.  Therefore, large-scale monitoring of DH substations in a network is challenging. Hence, in order to address these issues, we proposed a reference-group based monitoring approach. Herein, the operational monitoring of a DH substation, referred to as a target, is delegated to a reference-group which consists of DH substations experiencing a comparable operating regime along with the target. The approach was demonstrated on the monitoring of the return temperature variable for atypical\footnote{Here, "atypical" means that while it does not fit the definition of a normal operation, it is not faulty either and may also have some context.}  and faulty operational behavior in $778$ DH substations associated with multi-dwelling buildings. No target substation specific information related to its normal, atypical or faulty operation was used. Instead, information from the target's reference-group was leveraged to track its operational behavior. In this manner, $44$ DH substations were found where a possible deviation in the return temperature was detected earlier compared to models assuming overall operational homogeneity among the DH substations. In addition, six frequent patterns of deviating behavior in the return temperature of DH substations were identified based on the proposed reference-group based approach, which were then further corroborated by the feedback from a DH domain expert.