BMS Intervention Prediction to Reduce Forgotten Manual Overrides
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building management systems (BMS) often experience undesirable state changes due to manual interventions by occupants, leading to unintended temperature fluctuations and increased energy consumption, as these changes are frequently forgotten and not reverted in a timely manner.
Innovation Solution
A method is introduced that predicts the time of effect of interventions on BMS variables, providing feedback to users through a user interface, allowing for informed decisions on implementing or canceling changes, using machine learning models trained with historical data to determine the impact of interventions on energy consumption, zone air temperature, and other variables.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual intervention is allowed to change BMS configurations for occupant comfort, then occupant comfort is improved, but system stability deteriorates due to forgotten interventions causing undesirable state changes
Solution Approach 1:
The system provides automated feedback to occupants about the current state and predicted future state of BMS variables resulting from their interventions. This feedback loop allows occupants to make informed decisions and understand the consequences of their actions, preventing forgotten interventions from causing undesirable state changes while maintaining ease of operation.
Solution Approach 2:
The system performs preliminary prediction of intervention effects before the intervention is fully implemented. By using machine learning models to forecast future states and potential undesirable changes, the system allows operators to assess impacts in advance and make informed decisions about whether to proceed with the intervention, thus maintaining system stability.
2Ease of operation
If manual intervention is permitted to adjust BMS settings, then ease of operation is improved, but energy consumption increases due to unintended state changes
Solution Approach 1:
The system provides feedback on predicted energy consumption impacts of manual interventions, allowing operators to see the energy consequences before implementing changes. This enables informed decision-making that balances comfort needs with energy efficiency, preventing unintended energy-wasting state changes.
Solution Approach 2:
The system performs preliminary energy impact assessment using machine learning models to predict how manual interventions will affect energy consumption. This allows operators to evaluate energy consequences before implementing adjustments, preventing energy-wasting interventions while maintaining ease of operation.
3Device complexity
If intervention effects are not predicted, then system complexity is reduced, but measurement precision deteriorates regarding intervention impact timing
Solution Approach 1:
The system performs preliminary prediction of intervention effect timing and magnitude using machine learning models trained on historical BMS data. This allows accurate estimation of when and how interventions will affect system variables without requiring complex real-time simulation infrastructure, balancing measurement precision with acceptable system complexity.
Data Source
AI summary
A method of predicting a time of effect of an intervention of a point of a Building Management System (BMS). The method includes evaluating a first input to determine how an intervention of a point will affect a variable of the BMS; predicting a time at which the intervention will affect the variable of the BMS; presenting feedback to a user via a user interface before implementing the intervention of the point, the feedback comprising the time at which the intervention of the point is predicted to affect the variable; and implementing the intervention or a cancellation of the intervention based at least in part on a second input from the user or an automated response to the feedback. The method allows for users to determine whether to implement proposed interventions in real-time.