Inference server and environment controller for inferring via a neural network one or more commands for controlling an appliance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current environment control systems fail to generate optimal commands for appliances based on a combination of current environmental conditions and set points, as they either rely on simple rules that are ineffective or complex models that are difficult for humans to design, neglecting multiple interrelated criteria such as comfort, appliance stress, and energy consumption.
Innovation Solution
An environment controller and inference server system utilizing a neural network to receive environmental characteristic values and set points, transmitting them to an inference engine that generates optimal commands for controlling appliances, considering various criteria like comfort and energy efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a set of rules is implemented by the environment controller to generate commands, then the commands can be generated based on current environmental characteristic values and set points, but the rules become too complicated to be designed by a human being
Solution Approach 1:
The patent replaces the mechanical system of human-designed rule-based control with an artificial neural network system. The neural network learns optimal control strategies through training data, automatically generating commands that consider multiple interrelated criteria without requiring explicit programming of complex rules by humans.
Solution Approach 2:
The patent transforms the control approach from fixed rule-based parameters to dynamic parameters learned by the neural network. The system adjusts control commands based on learned patterns from training data, allowing flexible adaptation to different environmental conditions and appliance states without manual rule configuration.
2Ease of manufacture
If simple rules are used for command generation, then the system is easy to design, but the rules are too simple to generate effective commands that balance multiple criteria
Solution Approach 1:
The patent replaces simple rule-based control with a neural network-based control system that automatically learns complex control strategies. This substitution maintains ease of deployment (the neural network can be trained offline) while achieving effective command generation that balances multiple criteria through learned patterns rather than simple predefined rules.
3Ease of operation
If commands prioritize quick convergence from current temperature to target temperature, then comfort of people is improved, but stress on appliance components and energy consumption increase significantly
Solution Approach 1:
The neural network dynamically adjusts control parameters based on the temperature difference and other conditions. For small temperature differences, it generates conservative commands that minimize energy consumption and appliance stress. For large temperature differences, it balances comfort requirements with energy efficiency by learning optimal convergence rates from training data that includes energy consumption patterns.
Solution Approach 2:
The system uses feedback from environmental sensors and appliance state information to adjust control commands. The neural network learns from historical data how different control strategies affect energy consumption, appliance stress, and comfort, enabling it to optimize the balance between these competing objectives in real-time based on current conditions.
4Reliability
If commands prioritize minimizing stress on appliance components and energy consumption, then appliance preservation is improved, but the speed of convergence from current temperature to target temperature decreases
Solution Approach 1:
The neural network dynamically adjusts control parameters based on the temperature difference and appliance state. When the temperature difference is large, it allows faster convergence rates that temporarily increase stress on components. When the temperature difference is small, it prioritizes energy efficiency and component preservation. This dynamic parameter adjustment optimizes the balance between convergence speed, energy consumption, and appliance durability.
Data Source
AI summary
Inference server and environment controller for inferring one or more commands for controlling an appliance. The environment controller receives at least one environmental characteristic value (for example, at least one of a current temperature, current humidity level, current carbon dioxide level, and current room occupancy) and at least one set point (for example, at least one of a target temperature, target humidity level, and target carbon dioxide level); and forwards them to the inference server. The inference server executes a neural network inference engine using a predictive model (generated by a neural network training engine) for inferring the one or more commands based on the received at least one environmental characteristic value and the received at least one set point; and transmits the one or more commands to the environment controller. The environment controller forwards the one or more commands to the controlled appliance.