Executive Order 13423 and the Energy Independence and Security Act of 2007 require that U.S. federal agencies improve facility energy efficiency and reduce greenhouse gas emissions by 30% by 2015 relative to a 2003 baseline. Building energy systems often consume 20% more energy than is necessary due to system deviation from the design intent. Identifying the specific sources and root causes of energy waste in buildings can be challenging largely because energy flows are generally invisible and because of the diversity of potential problems.  Reducing the amount of energy wasted by building heating, ventilation and air conditioning (HVAC), lighting, and water systems can achieve much of these goals. The objective of this project was to demonstrate a whole-building performance monitoring and anomaly classification system at two Department of Defense (DoD) sites in partnership with Naval Station Great Lakes. Specific objectives of the technology demonstrations were to (1) identify, classify, and quantify building energy  consumption deviations from design intent or optimal, (2) support classification and identification of root causes of such deviation, (3) support recommendations for corrective actions, (4) quantify and prioritize the economic, energy of corrective actions, and (5) demonstrate that the building performance improves, ideally to its design intent, following implementation of corrective actions.

The software environment demonstrated integrates real-time building measurements and weather predictions with a simulation model, data mining, and anomaly detection algorithms. The computer simulation "reference model" represents the design intent of the building and includes HVAC, lighting, internal process loads, and water consumption. Instrumentation measures power and water flows. Data mining and anomaly detection algorithms identify and classify deviation from design intent.

The project successfully demonstrated:

• A real-time model-based whole-building performance monitoring and energy diagnostics tool using EnergyPlus has been developed and demonstrated at Naval Station Great Lakes.
• A framework for whole-building, simulation-based energy diagnostics has been established and demonstrated. Fault detection and diagnostics (FDD) algorithms based on statistical process control methods such as T² and Q statistics have been tested.
• A visualization dashboard for building performance energy monitoring and energy diagnostics has been developed and deployed in two real buildings. This dashboard provides an effective way for building facility managers to perform building performance decision-making.

The following energy faults were detected and diagnosed from the demonstration sites. These faults would waste more than 20% to 30% energy annually at the building level on two demonstration sites. Some faults would also cause issues related to thermal comfort. 

• Economizer faults: too much outside air intake during non-economizer modes,
• Lighting faults: lights on during unoccupied hours,
• Plug load faults: excessive plug load due to occupant behaviors,
• Chiller faults: chiller was off when commanded on due to control issues. These faults cause the air handling unit (AHU) discharge air temperatures and room temperatures to deviate from their respective setpoints. This causes building thermal comfort issues.

The facility managers at the Naval Base Great Lakes found:

• The energy usage visualization tool to be helpful as it enabled them to monitor impacts of control changes they made on energy consumption. 
• Faults and issues identified by the automated continuous commissioning tool were valued because the tool provided additional visibility into the building operation that was not provided by the existing building management system.  This additional information allowed the facility team to identify previously unknown operational issues and prioritize their maintenance actions.

All the instrumentation is standard commercial off-the-shelf products. Selected highlights that are relevant for future implantations are:

• Currently, the instrumentation cost is relatively high.  The largest components are the equipment and installation costs related to submetering and the on-site weather station. It is possible and reasonable to eliminate the on-site weather station by using weather data from the internet or an existing weather station on the base. There is a need for additional research efforts to establish cost-effective submetering.
• Internet access is critical for both cost reduction and tool development. 
• Building as-built drawings, control submittals, operation and maintenance records are very important to develop the energy models.
• It is desirable to have a centralized building management system (BMS) on the base, so the facility team member can remotely access the automated continuous commissioning system sitting in each building. Ideally, only one PC is needed to host the automated continuous commissioning system in the centralized BMS.
• Considering different scenarios of instrumentation cost, the typical simple pay back (SPB) for the automated continuous commissioning system is between 2.65 and 6.43, while the typical system savings to investment ratio (SIR) is between 1.13 and 2.75.