Control system for medium-sized commercial buildings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing HVAC systems in medium-sized commercial buildings face challenges in minimizing infection risk, improving air quality, and maximizing energy savings, particularly in the post-pandemic era, with a need for innovative methodologies and technologies that balance health and energy efficiency.
Innovation Solution
A cloud-based platform implementing model-based predictive control and model-free reinforcement learning to optimize HVAC operations by integrating occupancy prediction, weather forecasting, and indoor air quality modeling, which determines optimal rooftop unit control actions based on future states and sensor data to balance fresh air intake, air filtration, and energy usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If fresh air intake is increased to improve indoor air quality and minimize infection risk, then air quality improves, but energy consumption increases
Solution Approach 1:
The system performs preliminary forecasting of occupancy, weather, and air quality conditions to proactively adjust fresh air intake before critical periods occur. By predicting future states and pre-adjusting ventilation levels, the system maintains air quality while avoiding unnecessary energy consumption during periods when high ventilation is not needed.
Solution Approach 2:
The system dynamically adjusts fresh air intake levels based on real-time sensor data and forecasted conditions. Rather than maintaining a static high ventilation rate, the system modulates airflow continuously to match actual occupancy and air quality needs, thereby improving infection risk mitigation while minimizing energy waste during low-demand periods.
2Object-affected harmful factors
If air filtration and purification systems are activated to improve indoor air quality, then infection risk decreases, but energy usage increases
Solution Approach 1:
The system forecasts future air quality conditions and occupancy patterns to determine optimal times for activating filtration and purification systems. By anticipating periods when air quality degradation is likely or occupancy is high, the system activates these energy-intensive systems proactively rather than reactively, ensuring air quality maintenance while minimizing unnecessary energy consumption.
Solution Approach 2:
The system dynamically controls the operation of air filtration and purification systems based on real-time sensor readings and predicted conditions. Filtration intensity and system activation are continuously adjusted to match actual air quality needs, preventing both over-filtration (waste) and under-filtration (compromised air quality) by adapting to changing environmental and occupancy conditions.
3Use of energy by moving object
If HVAC operations are optimized for energy savings, then energy consumption decreases, but air quality and infection risk control may be compromised
Solution Approach 1:
The system uses forecasting capabilities to predict when energy-saving operations can be safely implemented without compromising air quality. By anticipating periods of low occupancy or favorable outdoor air quality conditions, the system can temporarily reduce ventilation or filtration intensity to save energy, knowing that air quality standards will still be met based on predicted conditions.
Solution Approach 2:
The system dynamically balances energy consumption and air quality control by continuously monitoring sensor data and adjusting HVAC operations in real-time. When outdoor conditions are favorable or occupancy is low, the system increases energy-saving operations. When sensor data indicates deteriorating air quality or rising occupancy, the system automatically intensifies ventilation and filtration, ensuring air quality maintenance while minimizing overall energy consumption through adaptive control.
Data Source
AI summary
An HVAC control system having a cloud-based optimization engine in communication with a local building hub that interfaces with the building HVAC system and room units. The cloud-based optimization engine implements an optimal and predictive control strategy to integrate occupancy prediction, weather forecasting, and modeling of indoor infection risk, indoor air quality, and building energy consumptions. The control strategy includes a model-based predictive control and a model-free reinforcement learning approach. The control strategy considers outdoor weather (both thermal and air quality) conditions, indoor occupancy and requirements for IAQ and infectious risk reduction to decide whether outdoor air should be introduced and how much fresh air will be introduced into the space. Communications with the building hub allow the local HVAC unit to be driven according to the optimization plan. Individual room sensing units can provide local sensor data to the cloud-based optimization engine.