Generation and representation of synthetic smart meter data
- PDF / 2,653,117 Bytes
- 16 Pages / 612 x 808 pts Page_size
- 34 Downloads / 255 Views
Generation and representation of synthetic smart meter data Research Article
Tianzhen Hong1 (), Daniel Macumber2, Han Li1, Katherine Fleming2, Zhe Wang1 1. Lawrence Berkeley National Laboratory, Berkeley, California, USA 2. National Renewable Energy Laboratory, Golden, Colorado, USA
Abstract
Keywords
Advanced energy algorithms running at big-data scale will be necessary to identify, realize, and verify energy savings to meet government and utility goals of building energy efficiency. Any algorithm must be well characterized and validated before it is trusted to run at these scales. Smart meter data from real buildings will ultimately be required for the development, testing, and validation of these energy algorithms and processes. However, for initial development and testing, smart meter data are difficult to work with due to privacy restrictions, noise from unknown sources, data accessibility, and other concerns which can complicate algorithm development and validation. This study describes a new methodology to generate synthetic smart meter data of electricity use in buildings using detailed building energy modeling, which aims to capture the variability and stochastics of real energy use in buildings. The methodology can create datasets tailored to represent specific scenarios with known truth and controllable amounts of synthetic noise. Knowledge of ground truth also allows the development and validation of enhanced processes which leverage building metadata, such as building type or size (floor area), in addition to smart meter data. The methodology described in this paper includes the key influencing factors of real-world building energy use including weather data, occupant-driven loads, building operation and maintenance practices, and special events. Data formats to support workflows leveraging both synthetic meter data and associated metadata are proposed and discussed. Finally, example use cases of the synthetic meter data are described to illustrate potential applications.
synthetic data,
1
Introduction
E-mail: [email protected]
EnergyPlus, data representation, building energy modeling, occupant modeling
Article History Received: 02 February 2020 Revised: 12 May 2020 Accepted: 13 May 2020 This is a U.S. government work and not under copyright protection in the U.S.; foreign copyright protection may apply 2020
enable reliable prediction of energy savings for specific ECMs and buildings. Although applying energy algorithms to real-world data is the end goal, adequate real datasets are often difficult to obtain and sometimes unavailable to the algorithm developers. Additionally, algorithm validation is made difficult when using real-world data because the ground truth is not known. For example, accurately calculating an algorithm’s non-routine event detection rate is not possible when the non-routine event’s occurrence in the data is not known. Another example is inadequately-trained learning algorithms, either due to having no metered data available (i.e., new constructions) or for buildings with c
Data Loading...
