System and method for controlling an HVAC system or an ACMV system of a building
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing HVAC and ACMV systems in multi-facility buildings face challenges in predicting thermal load demand variations due to dynamic human flow and diverse activities across different facilities, leading to sub-optimal thermal comfort and unnecessary energy consumption.
Innovation Solution
A system that generates facility-based occupancy patterns and predicts zone occupancy variations using historical data and real-time information, matches zones with pre-stored configurations from a historical database, and optimizes air handler configurations to determine optimal configuration combinations based on key performance indicators.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If HVAC system configuration is changed on board, then system operation is optimized, but it takes half hour or longer time to take effect on the building
Solution Approach 1:
The system performs preliminary prediction of thermal load demand at least half hour before the actual load occurs. By using historical data, occupancy patterns, and weather forecasts to predict future thermal conditions, the system pre-calculates optimal HVAC configurations in advance, so that when the configuration is applied, it immediately addresses the actual thermal needs rather than reacting with a half-hour delay.
2Measurement precision
If occupancy pattern prediction is based on single facility-type buildings, then prediction accuracy is improved for fixed patterns, but it cannot predict thermal load demand variation in multiple facilities-based buildings with dynamic human flow
Solution Approach 1:
The system segments the building into multiple facility types (e.g., retail, dining, entertainment, office) and creates separate occupancy patterns for each facility type based on historical data. This segmentation allows the system to capture the unique occupancy characteristics of each facility while maintaining overall building-wide prediction capability, making it adaptable to multi-facility buildings with dynamic human flow patterns.
Solution Approach 2:
The system transitions from static occupancy patterns to dynamic occupancy patterns that adapt to different facility types and time periods. By continuously learning from historical occupancy data and adjusting patterns based on facility-specific characteristics, the system can dynamically predict occupancy variations in multi-facility buildings rather than relying on fixed patterns designed for single facility types.
3Loss of energy
If thermal load demand is not predicted accurately in advance, then energy consumption is reduced through optimized control, but thermal comfort level of occupants becomes sub-optimal
Solution Approach 1:
The system incorporates feedback mechanisms that continuously monitor actual thermal conditions and occupancy patterns, comparing them against predicted values. This feedback is used to refine and update occupancy patterns and thermal load predictions, ensuring that energy optimization decisions are based on accurate, continuously improving data that maintains occupant thermal comfort while reducing energy consumption.
Solution Approach 2:
By predicting thermal load demand in advance with improved accuracy through multi-facility occupancy patterns, the system can pre-optimize HVAC configurations to match future thermal conditions. This preliminary optimization ensures that energy is not wasted on cooling or heating empty spaces while simultaneously maintaining thermal comfort when occupants are present, resolving the trade-off between energy efficiency and comfort reliability.
Data Source
AI summary
Embodiments provide a system for controlling HVAC/ACMV system of a building, including an occupancy pattern extractor configured to generate at least one facility-based occupancy pattern for each facility type based on historical occupancy data and spatial information of the building; a zone occupancy predictor configured to predict zone occupancy variation of each zone after a predetermined time period, based on the facility-based occupancy patterns and real-time occupancy data; a similar zone matcher configured to match each zone with one or more pre-stored zones and determine air handler configurations based on the matched pre-stored zones; a configuration generator configured to determine configuration combinations by combining the air handler configurations for a plurality of zones of the building, each configuration combination including one of the air handler configurations for each zone; and a configuration optimizer configured to determine an optimal configuration combination based on one or more key performance indicators.