Multivariate Smart Meter Compression Using PCA and Adaptive Batching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing smart meter data compression techniques only address individual variables, failing to exploit inter-relations among multiple variables and temporal correlations, leading to redundant data transmission and high bandwidth requirements.
Innovation Solution
A method employing Principal Component Analysis (PCA) to reduce dimensionality and Adaptive Multivariate Data Compression (AMDC) algorithm for temporal compression, determining an optimum batch size to minimize normalized root mean square error (nRMSE) and maximize bandwidth savings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If conventional single-variable compression techniques are used, then individual variable compression is achieved, but multivariate inter-dependency is ignored leading to redundant data transmission
Solution Approach 1:
The patent merges multiple single-variable compression techniques into a unified multivariate compression system that processes multiple variables simultaneously. The system combines PCA for dimensionality reduction with adaptive compression for temporal correlation exploitation, achieving synergistic compression across multiple dimensions while managing complexity through modular architecture.
Solution Approach 2:
The patent transitions from single-variable compression to multivariate compression by adding the dimension of variable inter-dependency. PCA transforms the data from original variable space to principal component space, exploiting correlations across multiple variables simultaneously, thereby achieving compression that single-variable methods cannot attain.
2Measurement precision
If high sampling rate is used for data collection, then data resolution is improved, but bandwidth requirement increases significantly
Solution Approach 1:
The patent applies compression techniques before data transmission to reduce the quantity of data that needs to be transmitted. By performing PCA and adaptive compression on high-resolution data locally, the system maintains measurement precision while significantly reducing the bandwidth requirement for transmitting the same information.
Solution Approach 2:
The patent changes the representation parameters of the data by transforming it from original variable space to principal component space. This parameter transformation allows the same information to be represented with fewer parameters, thereby reducing bandwidth requirements while preserving data resolution.
3Reliability
If all measured variables are transmitted continuously, then complete information is provided, but inter-variable correlations cause information redundancy
Solution Approach 1:
The patent extracts the essential information from multiple variables by identifying and transmitting only the principal components that capture the most significant variance. This extraction process removes redundant information while retaining the complete essential information needed for accurate reconstruction.
Solution Approach 2:
The patent transmits only a partial set of variables (principal components) rather than all original variables. By selecting the top k principal components that capture the majority of variance, the system achieves near-complete information transmission with significantly reduced redundancy.
4Quantity of substance
If multivariate compression is implemented, then bandwidth is reduced significantly, but compression algorithm complexity increases
Solution Approach 1:
The patent segments the compression process into distinct modular stages: PCA for dimensionality reduction, adaptive compression for temporal correlation exploitation, and variable selection. This segmentation allows each module to be optimized independently while achieving significant overall compression ratios.
Solution Approach 2:
The patent implements adaptive compression that dynamically adjusts compression parameters based on the characteristics of the input data. The system adapts to different data patterns and correlations, optimizing compression efficiency while managing computational complexity through dynamic parameter adjustment.
Data Source
AI summary
A smart sensing architecture (100) includes smart meters (102) and processing units (104). The smart meters (102) generate and transmit multidimensional data streams to the processing units (104). A processing unit (104) determines an optimum batch size for a multidimensional data stream and generates a multidimensional batch of data. The processing unit (104) reduces dimensionality of the multidimensional batch of data using principal component analysis to generate a low-dimensional batch of data and performs compressive sampling on the low-dimensional batch of data to generate a compressed batch of data, thereby saving bandwidth of transmission.