Neural Network Bypass for Legacy Environment Control Software Modules
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Legacy environment control software modules in building control systems are not resilient to changes and unexpected conditions, necessitating a method to seamlessly integrate neural networks for improved performance.
Innovation Solution
An environment controller with a communication interface and processing unit that transmits environmental characteristic values to an inference server executing a neural network engine, allowing the use of inferred output variables instead of those calculated by the legacy software module.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If neural network technology is used to replace legacy environment control software module, then resilience to changes and unexpected conditions is improved, but system complexity and integration difficulty increase
Solution Approach 1:
The patent introduces a software bridge layer that acts as an intermediary between the legacy environment control software module and the neural network technology. This bridge receives input variables from the legacy module, transmits them to the neural network inference engine, and receives inferred output variables in return. The intermediary approach allows the system to benefit from the resilience of neural networks while maintaining compatibility with existing legacy software architecture, thereby reducing integration complexity.
2Adaptability or versatility
If neural network inference engine is integrated into the environment controller, then control performance and adaptability are improved, but computational resource requirements and processing time increase
Solution Approach 1:
The neural network inference engine is pre-configured with a predictive model that has been trained in advance to perform environment control predictions. By preparing the predictive model beforehand with preprocessed data and established relationships, the system can quickly infer output variables during runtime without requiring extensive real-time computation, thus reducing processing time while maintaining high adaptability.
3Measurement precision
If neural network technology is deployed, then prediction accuracy and decision-making quality are improved, but energy consumption and computational load increase
Solution Approach 1:
The system implements selective neural network inference where the predictive model is only activated when needed based on specific conditions or thresholds. Rather than continuously running the neural network inference engine, the system uses the legacy software module for routine operations and only engages the neural network when enhanced prediction accuracy is required, thereby reducing overall computational energy consumption while maintaining high prediction accuracy when necessary.
Data Source
AI summary
Method and environment controller using a neural network for bypassing a legacy environment control software module. The environment controller receives at least one environmental characteristic value and determines a plurality of input variables. At least one of the plurality of input variables is based on one among the at least one environmental characteristic value. The environment controller transmits the plurality of input variables to an inference server executing a neural network inference engine. The environment controller receives at least one inferred output variable from the inference server. The environment controller uses the at least one inferred output variable received from the inference server in place of at least one output variable calculated by the legacy environment control software module based on the plurality of input variables. The environment controller may prevent the execution of the legacy software module or overwrite the output variable(s) calculated by the legacy software module.