Devices, methods, and systems for data-driven acceleration of deployed services
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for HVAC predictive modeling are resource-intensive and time-consuming, especially when calculating models for multiple buildings, requiring significant computing resources and time.
Innovation Solution
A data-driven approach utilizing a database of case pairs to rank and deploy HVAC resources efficiently across multiple buildings by comparing actual feature values to historical data, reducing the need for frequent model recalculations and resource usage through a ranking engine and deployment engine.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If predictive models are calculated multiple times for multiple buildings at a central location, then deployment accuracy and service performance are improved, but computing resource consumption and calculation time increase significantly
Solution Approach 1:
The system pre-calculates and stores deployment configurations in a database before actual deployment needs arise. Historical deployment data and building features are stored in advance, allowing the ranking engine to quickly retrieve and compare pre-processed information rather than performing full predictive model calculations during deployment operations.
Solution Approach 2:
Instead of recalculating full predictive models for each deployment scenario, the system creates simplified representations by storing key building features and deployment configurations as comparable data records. The ranking engine compares these stored representations to identify optimal deployments without performing resource-intensive model calculations.
2Productivity
If predictive models are calculated multiple times for multiple buildings, then deployment optimization is improved, but calculation time increases significantly
Solution Approach 1:
Building features, deployment configurations, and historical performance data are pre-processed and stored in the database before deployment operations. This preliminary preparation allows the ranking engine to perform rapid comparisons using stored data rather than performing time-consuming model calculations during actual deployment decision-making.
Solution Approach 2:
The system extracts only the essential building features and deployment parameters needed for comparison and stores them separately in the database. This extraction of key information allows the ranking engine to perform rapid comparisons without processing complete predictive models, significantly reducing calculation time while maintaining deployment optimization quality.
3Measurement precision
If full predictive models are used for each building deployment decision, then deployment precision is improved, but system complexity and resource requirements increase
Solution Approach 1:
The system creates simplified data representations of building features and deployment configurations that capture the essential characteristics needed for accurate deployment decisions. These simplified records serve as proxies for full predictive models, enabling precise deployment matching without the computational complexity of maintaining and executing complete models for each comparison.
Solution Approach 2:
The ranking engine acts as an intermediary between building features and deployment configurations, using a simplified comparison mechanism that ranks match quality without requiring full predictive model execution. This intermediary approach maintains deployment precision by systematically evaluating multiple factors while avoiding the complexity of direct model-based optimization.
Data Source
AI summary
Devices, methods, and systems for data-driven acceleration of deployed services are described herein. One system includes a database configured to store a plurality of case pairs that correspond to previously calculated models, wherein the previously calculated models are based on a number of features, and wherein each of the plurality of case pairs comprise a first value representative of the number of features and a second value representative of deployed heating, ventilation, and air conditioning (HVAC) resources, a ranking engine configured to rank each of the plurality of case pairs based on a performance of the deployed services, and a deployment engine configured to: receive actual feature values, and deploy HVAC resources based on a comparison between the actual feature values and the plurality of ranked case pairs.