Predictive daylight harvesting system
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current daylight harvesting systems are inefficient due to reliance on basic rules of thumb for design, lack of suitable simulation tools, and inability to quantify performance, leading to suboptimal energy savings and occupant comfort in buildings and greenhouses.
Innovation Solution
A predictive daylight harvesting system that uses a combination of sensors, mathematical models, and artificial intelligence to simulate and optimize daylight usage based on historical weather data, occupant behavior, and plant growth, adjusting lighting and fenestration devices to maximize energy savings while maintaining comfortable environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If basic rules of thumb are used for daylight harvesting system design, then the system can be implemented with simple methods, but the energy savings and occupant comfort are suboptimal
Solution Approach 1:
The system performs preliminary simulations using historical weather data and mathematical models to predict future daylight conditions before actually controlling the lighting. This allows the system to pre-calculate optimal lighting strategies based on predicted sky conditions, transforming the simple reactive approach into a proactive predictive system that achieves both ease of implementation and optimal energy savings
Solution Approach 2:
The system creates a virtual model (copy) of the physical environment including building geometry, fenestration characteristics, and interior surfaces. This virtual model is used for simulations to predict daylight distribution without requiring complex physical measurements, enabling accurate predictive control while maintaining simple implementation through software-based modeling
2Productivity
If predictive simulation tools are implemented, then energy savings can be maximized, but the system complexity increases
Solution Approach 1:
The system employs a single mathematical model that serves multiple functions: predicting sky conditions, calculating solar radiation distribution, simulating interior daylight levels, and determining optimal lighting control strategies. This multi-functional approach maximizes energy savings through comprehensive predictive capability while avoiding the complexity of multiple separate specialized tools
Solution Approach 2:
The system introduces a virtual model as an intermediary between the physical environment and the control system. This virtual model acts as a mediator that captures complex environmental interactions through simplified mathematical representations, enabling accurate predictions without requiring complex physical sensing and control infrastructure
3Measurement precision
If historical weather data and mathematical models are used for prediction, then daylight usage can be accurately predicted, but the computational requirements and system complexity increase
Solution Approach 1:
The system pre-calculates and stores sky condition predictions and solar radiation distributions based on historical weather data and mathematical models. By performing these computationally intensive calculations in advance rather than in real-time, the system achieves high prediction accuracy while keeping real-time computational requirements manageable
Solution Approach 2:
The system uses a virtual model that replicates the physical environment's geometric and optical characteristics. This copy allows the system to perform accurate predictive simulations by mathematically modeling light transport and solar radiation without requiring complex real-time measurements or computations on the actual physical system
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables interactive simulation and self-tuning of daylight harvesting systems to achieve annual energy savings of 40-50% by accurately predicting and adjusting daylight usage, improving both energy efficiency and occupant comfort.
Implementation Method 1
Measurement data from one or more photosensors is obtained that provides measurements of an initial distribution of direct and interreflected radiation within the environment
Data Source
AI summary
A predictive system and method thereof for indoor horticulture are disclosed. The method includes obtaining a set of input values identifying a geographic position of a physical structure enclosing an interior environment and a target distribution for environmental parameters for a selected plant occupant. The method further includes obtaining a virtual representation of the physical structure, and iteratively over time, updating the virtual representation based on actual plant growth or a predicted plant growth model for the selected plant occupant. The method further includes running a computational model to obtain a predicted distribution of the environmental parameters for the virtual representation, and determining a target distribution of artificially modulated environmental parameters. Based on the target distribution of the artificially modulated environmental parameters, the method includes setting output parameters for control devices to collectively control the actual distribution of the set of environmental parameters.