System and method for building energy use improvement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional HVAC systems are inefficient due to manual and static setpoint controls, leading to excessive energy consumption and increased operational costs, as they fail to account for variables like building occupancy, weather, and energy prices.
Innovation Solution
An energy efficiency application that utilizes real-time sensor data and a machine learning model to dynamically adjust HVAC setpoints, optimizing energy consumption while maintaining occupant comfort and safety.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If manual and static setpoint controls are used in conventional HVAC systems, then system simplicity and ease of operation are maintained, but energy consumption increases and system efficiency deteriorates
Solution Approach 1:
The patent transforms static setpoint controls into dynamic, adaptive controls that automatically adjust HVAC parameters based on real-time sensor data from multiple sources (occupancy sensors, weather stations, energy price signals). This dynamic adaptation enables the system to optimize energy consumption continuously without manual intervention, directly resolving the contradiction between energy efficiency and system complexity.
Solution Approach 2:
The HVAC system performs self-optimization through automated machine learning models that continuously learn from historical and real-time data, eliminating the need for manual calibration and adjustment. The system autonomously adapts to changing conditions (occupancy patterns, weather, energy prices) and self-adjusts setpoints, reducing energy consumption without requiring complex manual control procedures.
2Adaptability or versatility
If static setpoints are used throughout the year, then control simplicity is maintained, but the system cannot adapt to variable conditions such as occupancy, weather, and energy prices, resulting in surplus energy consumption
Solution Approach 1:
The patent implements multi-loop feedback mechanisms where sensor data from occupancy detectors, weather stations, and energy market systems continuously feeds back to the machine learning models. These models process the feedback signals and automatically adjust setpoints in real-time, enabling the system to adapt to variable conditions and eliminate surplus energy consumption while maintaining control simplicity through automation.
Solution Approach 2:
The system dynamically changes multiple operational parameters (temperature setpoints, humidity levels, ventilation rates, equipment scheduling) based on real-time conditions. The machine learning models optimize these parameters continuously by learning from historical data and responding to current sensor inputs, allowing the HVAC system to adapt to occupancy patterns, weather variations, and energy price signals without manual intervention.
3Loss of information
If manual configuration and calibration are performed at equipment level, then system complexity is minimized, but the system cannot account for building-level variables such as occupancy, grid load, and emissions
Solution Approach 1:
The patent creates a universal building management platform that consolidates multiple control functions (HVAC optimization, occupancy management, weather response, energy market participation, emissions tracking) into a single integrated system. The machine learning models serve multiple purposes simultaneously, analyzing diverse data sources and coordinating adjustments across different building systems, thereby capturing comprehensive building variable information without proportionally increasing complexity.
Solution Approach 2:
The patent introduces building management systems and centralized control platforms as intermediary layers between individual equipment and the various data sources (sensors, weather stations, energy markets). These intermediaries aggregate and process information from multiple sources, performing coordinated optimization across the entire building rather than at isolated equipment levels, thereby enabling comprehensive variable accounting while managing complexity through hierarchical organization.
Data Source
AI summary
A method for modifying energy consumption by a building includes receiving sensor data generated by a sensor, where the sensor data is indicative of at least one of a mixed air temperature, an outside air temperature, or air tonnage. The method further includes providing the sensor data as input into a computer-implemented machine learning model that is trained by way of reinforcement learning. The method also includes computing a setpoint modification through use of the machine learning model, where energy consumption is reduced based upon an HVAC system for the building implementing the setpoint modification.