Automated VEE Rules Configuration for Energy Data Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Real-time and near real-time energy consumption systems face challenges in accurately processing energy consumption data due to intermittent errors and anomalies, leading to suboptimal validation, estimation, and editing (VEE) techniques, which are often labor-intensive and result in less accurate post-VEE data.
Innovation Solution
An automated VEE rules configuration engine dynamically optimizes VEE techniques for individual energy consumption data streams, using training data, facility models, and post-VEE readings to create anomaly estimates and select appropriate estimation techniques, thereby improving data accuracy and reducing manual labor.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If automated VEE rules configuration engine is implemented, then data accuracy is improved, but device complexity increases
Solution Approach 1:
The VEE rules configuration engine automatically generates and optimizes validation, estimation, and editing rules without requiring manual configuration. The system self-configures by processing training data, identifying patterns and anomalies, and dynamically creating appropriate VEE rules for different data streams, thereby improving data accuracy while avoiding the need for complex manual rule setup
Solution Approach 2:
The engine dynamically adjusts VEE rule parameters based on analysis of training data characteristics. By changing parameters such as anomaly thresholds, estimation methods, and validation criteria according to the specific patterns observed in the data, the system achieves high data accuracy without requiring fixed complex rule sets for all scenarios
2Productivity
If manual VEE techniques are used, then labor costs are high, but implementation simplicity is maintained
Solution Approach 1:
The system replaces manual mechanical processes of VEE rule configuration with an automated computational engine. The engine uses algorithms to process training data, identify anomalies, and generate VEE rules automatically, substituting human labor with an automated system that improves productivity while managing complexity through software-based solutions
Solution Approach 2:
The engine creates standardized VEE rule templates based on patterns learned from training data. By copying and adapting proven rule structures from the training phase to production data streams, the system achieves high productivity through automated rule generation while maintaining manageable complexity through template-based approaches
3Measurement precision
If dynamic optimization of VEE techniques is performed, then post-VEE data accuracy is improved, but processing time increases
Solution Approach 1:
The system performs preliminary analysis during the training phase by processing training data to identify patterns, anomalies, and optimal VEE rules before deployment. This preliminary action creates a library of optimized rules that can be quickly applied to production data, achieving high post-VEE data accuracy without excessive processing time during actual operation
Solution Approach 2:
The VEE rules configuration engine dynamically adjusts and optimizes rules based on the specific characteristics of each data stream and anomaly type. By making rules adaptive rather than static, the system achieves high accuracy for diverse scenarios while managing processing time through efficient dynamic adjustment mechanisms
Data Source
AI summary
An energy control system includes training data stores, a facility model processor, a post VEE readings data stores, a VEE configuration engine, and a global model module. The facility model processor employs interval based energy consumption streams corresponding to a facility to develop and maintain weather-normalized baseline energy consumption data for the facility. The post VEE readings data stores tagged energy consumption data sets that are each associated with a corresponding one of said interval based energy consumption streams, each of said tagged energy consumption data sets comprising groups of contiguous interval values tagged as having been validated, wherein said groups correspond to correct data. The VEE configuration engine reads the post VEE readings data stores upon initiation of an event and, for the each of the tagged energy consumption data sets, creates anomalies having different durations using only the groups of contiguous interval values, and generates estimates for the anomalies by employing estimation techniques and, for each of the different durations, selects one of the estimation techniques for subsequent employment when performing VEE of subsequent energy consumption data for the corresponding one of the interval based energy consumption streams. The global model module receives the weather-normalized baseline energy consumption data and post VEE readings data, and develops an energy consumption model based on the weather-normalized baseline energy consumption data and the post VEE readings data, and controls overall energy consumption within the facility based on the energy consumption model by scheduling run times of one or more building elements.