Multimodal Signal Compression for Bandwidth-Limited Edge Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Transmitting large amounts of high-resolution raw sensor data in power systems, such as in the PowerGenome architecture, is unfeasible due to bandwidth limitations, requiring significant computing and storage resources, which is economically and technically challenging.
Innovation Solution
Implementing data featurization and compression techniques using sparse wavelet transforms and artificial neural networks, specifically autoencoders, to reduce data transmission by recording and storing only the difference between subsequent signals, thereby reducing computing resources and data size by several orders of magnitude.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If high-resolution raw sensor data is transmitted over the network, then measurement precision is improved, but data transmission bandwidth requirements increase significantly
Solution Approach 1:
The patent extracts and transmits only the essential features of the signal rather than the complete raw data. By performing featurization that identifies and transmits only the most relevant signal characteristics, the system maintains measurement precision while dramatically reducing the volume of data that needs to be transmitted over the network.
Solution Approach 2:
The patent transforms the signal from its original high-dimensional raw form into a lower-dimensional feature representation. This parameter transformation maintains the essential information needed for measurement precision while changing the data structure to require significantly less transmission bandwidth.
2Loss of information
If large amounts of raw data are stored at the edge device, then data availability is improved, but storage requirements and computing resources increase significantly
Solution Approach 1:
The patent extracts only the essential features from the raw sensor data and stores these extracted features at the edge device instead of storing the complete raw data. This extraction process maintains data availability for analysis while dramatically reducing the storage capacity required at edge devices with limited resources.
3Loss of information
If complete raw data is transmitted to the cloud, then data completeness is improved, but network bandwidth consumption increases significantly
Solution Approach 1:
The patent extracts and transmits only the most relevant features from the raw sensor data to the cloud, maintaining data completeness for analysis purposes while dramatically reducing network bandwidth consumption. The extraction process identifies and transmits only the essential information needed for power system optimization.
Solution Approach 2:
The patent applies partial action by transmitting a subset of the most important signal features rather than the complete raw data set. This partial transmission approach provides sufficient information for cloud-based analysis while consuming significantly less network bandwidth.
4Productivity
If high computational power is used for data processing at the edge device, then processing speed is improved, but device complexity and power consumption increase
Solution Approach 1:
The patent extracts only the essential features from raw sensor data using simplified processing algorithms suitable for edge devices with limited computational resources. This extraction approach maintains processing speed while avoiding the need for complex high-power computational hardware at the edge.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
There is provided a data transmission and compression method arranged to compress and transmit data between an edge device and a remote server. The method comprises collecting data at the edge device, wherein the data is attributed to a plurality of signal signatures; generating a data matrix at the edge device; transforming the data matrix, wherein transforming the data comprises using a wavelet transform; compressing the data, wherein compressing the data comprises utilising an autoencoder; and transmitting the encoded compressed data to the remote server via a communication channel. The method further comprises, at the remote server, decompressing the data utilising an autoencoder; reconstructing the signal signatures using an inverse wavelet transform; and storing the reconstructed data signatures in a datastore on the remote server.