Building supervisory control system having safety features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cloud-based supervisory control systems for building HVAC face issues with reliability and safety, particularly when machine learning models are suboptimal, leading to potential discomfort, loss of connectivity, and lack of customer control.
Innovation Solution
Implementing a safety features stack that includes connectivity check automated fail-over, optimization watchdog, rule-based comfort protection mechanism, savings bottlenecks overview, and human override to ensure system reliability and customer control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If cloud-based supervisory control system is implemented, then energy performance is improved, but system reliability deteriorates due to potential loss of connectivity
Solution Approach 1:
The system performs preliminary actions by implementing connectivity checks and automated fail-over mechanisms before complete system failure occurs. The supervisory controller continuously monitors cloud connectivity and automatically switches to local control mode when connectivity is lost, preventing system failure and maintaining reliability while preserving energy optimization capabilities.
Solution Approach 2:
An intermediary mechanism is introduced between the cloud-based supervisory controller and the HVAC system. This intermediary layer includes local control logic and automated fail-over capabilities that mediate between cloud connectivity and system operation, ensuring continuous reliable control even when cloud connection is interrupted.
2Use of energy by moving object
If machine learning model is used for optimization, then energy efficiency is improved, but comfort reliability deteriorates when model is suboptimal or incorrect
Solution Approach 1:
A feedback mechanism is implemented where the supervisory controller continuously monitors building conditions and comfort parameters. When the machine learning model produces suboptimal or incorrect results, the system detects this through feedback from sensors and performance metrics, automatically adjusts control parameters, or switches to alternative control strategies to maintain comfort reliability while preserving energy efficiency gains.
Solution Approach 2:
The control system is made dynamic by allowing automatic switching between different control modes (cloud-based optimization, local control, manual override). This dynamic adaptability enables the system to respond to model performance issues in real-time, maintaining comfort reliability while preserving the energy efficiency benefits of machine learning when it performs well.
3Productivity
If automated control system is implemented, then productivity is improved, but ease of operation deteriorates due to loss of customer control
Solution Approach 1:
The system implements dynamic control authority allocation that allows customers to adjust their level of automation between fully automated mode and manual override mode. This dynamic flexibility enables customers to switch to manual control when they need direct control, maintaining ease of operation while preserving productivity benefits during automated operation.
Solution Approach 2:
An intermediary interface is provided between the automated control system and the customer. This interface includes notification mechanisms and override capabilities that mediate between automated decision-making and customer control needs, allowing customers to maintain ease of operation through simple overrides while preserving productivity during normal automated operation.
4Reliability
If safety features stack is added, then system reliability is improved, but device complexity increases
Solution Approach 1:
Multiple safety features are merged into an integrated stack that includes connectivity checks, automated fail-over, comfort protection mechanisms, and notification systems. By combining these features into a unified architecture with shared components and centralized control logic, the system achieves high reliability while minimizing the complexity increase that would result from implementing each feature separately.
Solution Approach 2:
The safety features stack implements multi-functional components that serve multiple purposes. For example, the supervisory controller not only performs energy optimization but also monitors connectivity, detects comfort issues, and manages fail-over operations. This universality reduces overall system complexity by eliminating redundant components while maintaining comprehensive safety and reliability.
Data Source
AI summary
A building supervisory control structure having a supervisor connectable to a cloud and a heating, ventilation and air conditioning (HVAC) unit connected to the supervisor and the cloud. A safety features stack is connected to the supervisor. The safety features stack includes a connectivity check automated fail-over, an optimization watchdog, a rule-based comfort protection mechanism, savings bottlenecks overview, a human override, and a notification mechanism.