Network-on-Chip Sensor Data Encoding for Low Power Edge Transmission
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional network-on-chip technologies face challenges in reducing power consumption, making it difficult to implement them in edge devices where power efficiency is crucial.
Innovation Solution
A network-on-chip is designed to encode data from various sensors, including image and non-image data, and is capable of operating at low power. It includes first and second data converters that process image and non-image data respectively, filtering redundant data and assigning weights based on data processing formats like RGB and YUV, before transmitting the encoded data to an external server in burst lengths.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If conventional network-on-chip technology is used to exchange data at high speed, then data transmission speed is improved, but power consumption increases
Solution Approach 1:
The patent extracts and removes redundant data from sensor inputs before processing and transmission. By identifying and eliminating duplicate or unnecessary data elements, the system reduces the total data volume that requires high-speed transmission, thereby lowering power consumption while maintaining essential data exchange functionality
Solution Approach 2:
The patent applies different encoding schemes based on data characteristics and transmission requirements. By changing encoding parameters dynamically - using more compact representations for redundant data and optimized formats for critical data - the system achieves efficient transmission with reduced power consumption compared to conventional uniform high-speed transmission
2Loss of information
If all sensor data is transmitted without filtering, then data completeness is improved, but data transmission volume and power consumption increase
Solution Approach 1:
The patent extracts only the essential and non-redundant information from sensor data streams. By applying filtering mechanisms that identify and remove duplicate data while preserving unique information, the system maintains data completeness for meaningful content while significantly reducing transmission volume and associated power consumption
Solution Approach 2:
The patent applies different processing and filtering quality levels to different data streams based on their importance and characteristics. Critical data receives minimal filtering to preserve completeness, while redundant data streams undergo aggressive filtering, optimizing the balance between information retention and energy consumption
Data Source
AI summary
Disclosed is a network-on-chip including a first data converter that receives first image data and second image data from at least one image sensor and encodes one image data among the first image data and the second image data, into first data, based on whether the first image data is identical to the second image data and a second data converter that receives non-image data from at least one non-image sensor and encodes the received non-image data into second data. The network-on-chip outputs the first data and the second data to transmit the first data and the second data to an external server at a burst length.