Assisted point mapping to enable cost-effective deployment of intelligent building applications.

Number: pap. 3361

Author(s) : LEONARDI F., REEVE H. M., WAGNER T. C., et al.

Summary

Over the past years intelligent building applications that promise to dramatically reduce energy consumption, improve occupant comfort and streamline maintenance have been proposed. However their adoption has met a steep barrier in the unexpectedly high cost of mapping data from building automation systems into these applications’ data models. In fact the industry does not have a common convention on how to name points. Generally, names are correlated with the semantic of the variables they represent, but typically engineers have the freedom to set up variable names according to their preferences. In the last few years the research community has devoted increasing attention in automating the process of mapping data points from existing BAS. In order to meet market requirements, an “ideal” algorithm must be accurate, able to infer complex relationships between data points, easy to use, and scalable. However, none of the published work meets all the market requirements. Most need an expert user, some are not “easy to use” and none can automatically infer complex relationships. This paper presents a novel algorithm to tackle the mapping problem. This work contributes to the state-of-the-art by providing an algorithm that can be successfully applied to various datasets with minor or no modification to the algorithm (i.e. no expert in the loop). This is also the first to automatically infer complex relationships with only point names as input (i.e. ease of use). The algorithm was tested against a large and diversified dataset comprising points from five buildings, two vendors, three distributors and more than 20K points. The algorithm correctly mapped over 90% of the points required by a test application and successfully identified over 90% of VAVs and 80% of AHUs.

Available documents

Format PDF

Pages: 8 p.

Available

  • Public price

    20 €

  • Member price*

    15 €

* Best rate depending on membership category (see the detailed benefits of individual and corporate memberships).

Details

  • Original title: Assisted point mapping to enable cost-effective deployment of intelligent building applications.
  • Record ID : 30019247
  • Languages: English
  • Subject: Environment
  • Source: 2016 Purdue Conferences. 4th International High Performance Buildings Conference at Purdue.
  • Publication date: 2016/07/11

Links


See other articles from the proceedings (77)
See the conference proceedings