The surge in interval meter data availability and associated activity in energy data analytics has inspired new interest in advanced methods for building efficiency savings estimation. Statistical and machine learning approaches are being explored to improve the energy baseline models used to measure and verify savings. One outstanding challenge is the ability to identify and account for operational changes that may confound savings estimates. In the measurement and verification (M&V) context, 'non-routine events' (NREs) cause changes in building energy use that are not attributable to installed efficiency measures, and not accounted for in the baseline model's independent variables. In the M&V process NREs must be accounted for as 'adjustments' to appropriately attribute the estimated energy savings to the specific efficiency interventions that were implemented. Currently this is a manual and custom process, conducted using professional judgment and engineering expertise. As such it remains a barrier in scaling and standardizing meter-based savings estimation. In this work, a data driven methodology was developed to (partially) automate, and therefore streamline the process of detecting NREs in the post-retrofit period and making associated savings adjustments. The proposed NRE detection algorithm is based on a statistical change point detection method and a dissimilarity metric. The dissimilarity metric measures the proximity between the actual time series of the post-retrofit energy consumption and the projected baseline, which is generated using a statistical baseline model. The suggested approach for NRE adjustment involves the NRE detection algorithm, the M&V practitioner, and a regression modeling algorithm. The performance of the detection and adjustment algorithm was evaluated using a simulation-generated test data set, and two benchmark algorithms. Results show a high true positive detection rate (75%-100% across the test cases), higher than ideal false positive detection rates (20%-70%), and low errors in energy adjustment (<0.7%). These results indicate that the algorithm holds for helping M&V practitioners to streamline the process of handling NREs. Moreover, the change point algorithm and underlying statistical principles could prove valuable for other building analytics applications such as anomaly detection and fault diagnostics.

As building energy and system-level monitoring becomes more common, facilities teams are faced with an overwhelming amount of data. This data does not typically lead to insights, corrective actions, and energy savings unless it is stored, organized, analyzed, and prioritized in automated ways. The Smart Energy Analytics Campaign is a public-private sector partnership program focused on supporting commercially available energy management and information systems (EMIS) technology use and monitoring-based commissioning (MBCx) practices. MBCx is an ongoing commissioning process with focus on analyzing large amounts of data on a continuous basis. EMIS tools are used in the MBCx process to organize, present, visualize, and analyze the data. With Campaign data from over 400 million square feet (sq ft) of installed space, this paper presents the results achieved by owners that are implementing EMIS, along with associated technology costs. The study's EMIS users that reported savings achieved median cost savings of $0.19/sq ft and 7 percent annually, with savings shown to increase over time. For 35 portfolio owners, median base cost to install an EMIS was $0.03/sq ft, with an annual recurring software cost of $0.02/sq ft and estimated annual labor cost of $0.03/sq ft. Two types of EMIS systemsenergy information systems and fault detection and diagnostic systems-are defined in the body of the paper. Of the two, we find that fault detection and diagnostic systems have both higher savings and higher costs. The paper offers a characterization of EMIS products, MBCx services, and trends in the industry.

The core purpose of this report was to collect data that would be of use in promoting commissioning of new and existing buildings. A secondary purpose was to define methods for determining costs, benefits, and persistence of commissioning along with understanding national differences in the definition of commissioning. Research was grouped under two broad headings: Commissioning Cost-Benefit, and Commissioning Persistence. Commissioning Cost-Benefit Literature Review of Commissioning Cost-Benefit Methodologies Twelve studies were summarized, focused on studies where the cost-benefit methodologies were known. The majority were research studies of multiple buildings, and the studies ranged from research reports, databases, and marketing literature. These studies are summarized in three main aspects: 4. What problems were found, and the solutions, and 5. Non-energy benefits. Collected data was collated in spreadsheets for analysis and generation of charts of the key findings. Commissioning Persistence Literature Review on the Persistence of Commissioning Benefits This review summarized the findings from five studies encompassing 37 commissioning projects from across the USA. Persistence of savings was expressed as a percentage of the original claimed savings, after a specified time has elapsed after the project (e.g., 75 % after five years). In addition to evaluating project savings, the studies covered persistence at the level of specific measures, including the reasons for measures not persisting. Impact of Savings Normalization Method on Commissioning Persistence This study reviewed two weather normalization methods that are used in calculating energy savings from commissioning, and compared their impact on commissioning persistence claims. The two methods evaluated were: International Performance Measurement and Verification Protocol (IPMVP) A baseline regression model (or calibrated simulation model) is created based on the precommissioning energy use and recorded temperature/humidity. In the post-commissioning period, weather data is collected, and the regression model is used to predict what the energy use would have been if commissioning hadn't occurred. The actual energy use is subtracted from the modeled prediction, and this constitutes the energy saved. Normalized Annual Consumption (NAC) Similar basic principle to the IPMVP; a regression model (or calibrated simulation model) is created using baseline data. This model is applied to a standardized 'average' weather year based on the site location in order to calculate baseline annual energy use. In the postcommissioning period the regression model is recreated using post-energy and post-weather data, and this regression model is applied to the same 'average' weather year. The difference between the two modeled average years constitutes the savings. Examples of Tools for Enhancing Persistence of Commissioning Benefits There are a number of data collection and analysis tools that may be used for monitoring the persistence of commissioning improvements. This...

No abstract

No abstract