Building Automation Data Cleansing via Adaptive Error Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building automation systems face challenges in detecting and cleansing suspect data due to varying data quality and types, which can lead to errors and inaccuracies in measurement and verification (M&V) and demand response (DR) algorithms.
Innovation Solution
A method using processing electronics to automatically select appropriate error detectors and data cleansers based on data type and intended use, employing detectors like static bounds, adaptive bounds, derivative bounds, and stuck value detectors, and cleansers such as interpolation, formatting, and sorting, to identify and correct suspect data points.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple error detectors and data cleansers are available to handle varying data quality, then data accuracy and reliability are improved, but system complexity increases
Solution Approach 1:
The system divides data quality control into separate functional modules: multiple specialized error detectors (static bounds, adaptive bounds, derivative bounds, stuck value detectors) and data cleansers (replacement, interpolation, formatting, sorting). Each module handles specific types of data errors, allowing the system to maintain high reliability through specialized processing while managing complexity through modular architecture.
Solution Approach 2:
The system dynamically selects which error detectors and data cleansers to apply based on real-time analysis of data characteristics and quality metrics. Rather than applying all possible corrections uniformly, the system adapts its processing strategy to the specific data being analyzed, improving reliability where needed while reducing unnecessary processing complexity.
2Ease of operation
If automatic selection of error detectors and cleansers is implemented, then ease of operation is improved, but device complexity increases
Solution Approach 1:
The system performs self-selection of appropriate error detectors and data cleansers based on automatic analysis of data characteristics. The processing electronics evaluate data quality metrics and autonomously determine which correction methods to apply, eliminating the need for manual configuration while implementing sophisticated automated decision-making logic.
Solution Approach 2:
The system continuously monitors data quality metrics and uses this feedback to adjust its processing strategy. By analyzing the effectiveness of applied corrections and the characteristics of remaining data issues, the system refines its automatic selection process, improving ease of operation through adaptive automation.
3Adaptability or versatility
If data from disparate sources with varying qualities is processed, then adaptability is improved, but measurement precision deteriorates
Solution Approach 1:
The system applies different error detection and correction strategies tailored to the specific characteristics of each data source and data type. Rather than using a uniform processing approach, it adjusts detection thresholds, selection criteria, and correction methods to match the local quality characteristics of each data source, thereby maintaining measurement precision while handling diverse data.
Solution Approach 2:
The system dynamically adjusts processing parameters such as detection thresholds, correction thresholds, and selection criteria based on the characteristics of the input data. By changing these parameters adaptively, the system maintains high measurement precision across disparate data sources while preserving its ability to handle varying data qualities.
Data Source
AI summary
A method for detecting and cleansing suspect building automation system data is shown and described. The method includes using processing electronics to automatically determine which of a plurality of error detectors and which of a plurality of data cleansers to use with building automation system data. The method further includes using processing electronics to automatically detect errors in the data and cleanse the data using a subset of the error detectors and a subset of the cleansers.