Multi-access edge computing for remote construction hazard prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Construction sites face challenges with connectivity, bandwidth, cybersecurity, and quality of service due to the dynamic and chaotic nature of remote environments, limiting the effectiveness of IoT systems in providing comprehensive safety monitoring and risk prediction.
Innovation Solution
A multi-access edge computing system that integrates heterogeneous sensors, AI components, and Software Defined Networking (SDN) for real-time safety monitoring, combining sensor data with user feedback to generate control signals for equipment operation and predict hazards, utilizing a distributed framework that processes data locally and in the cloud for efficient data management and security.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If cloud computing is used for processing construction site data, then comprehensive data analysis and risk prediction can be achieved, but connectivity issues and bandwidth limitations in remote locations prevent reliable data transmission
Solution Approach 1:
The computing system is segmented into three distinct layers: edge computing devices deployed at remote construction sites for local data processing, intermediate servers for regional data aggregation and storage, and cloud computing resources for comprehensive analysis. This segmentation allows each component to operate independently with appropriate computational capabilities, ensuring that critical processing occurs locally even when cloud connectivity is unavailable.
Solution Approach 2:
Intermediate servers act as mediators between edge computing devices and cloud computing resources. These servers provide local data storage and processing capabilities at regional locations, enabling edge devices to offload data when cloud connectivity is unavailable. The intermediate layer bridges the gap between remote edge devices and centralized cloud resources, ensuring continuous operation during network disruptions.
2Measurement precision
If more sensors and monitoring equipment are deployed to improve safety monitoring coverage, then hazard detection capability is enhanced, but connectivity and bandwidth limitations prevent effective data transmission from all sensor locations
Solution Approach 1:
Sensor networks are organized into distributed edge computing zones where local edge devices aggregate and pre-process data from multiple sensors before transmission. This segmentation reduces the total volume of data requiring network transmission while preserving all critical hazard detection information through local intelligent filtering and prioritization.
Solution Approach 2:
Edge computing devices perform preliminary data processing, filtering, and analysis at the source before transmission to intermediate servers or cloud. Critical hazard indicators are identified and prioritized locally, ensuring that only essential information consumes bandwidth during transmission, thereby preventing information loss despite limited connectivity.
3Loss of time
If real-time data processing is implemented for immediate hazard detection, then response time is reduced, but bandwidth consumption increases significantly in remote locations with limited connectivity
Solution Approach 1:
Processing operations are segmented into three tiers based on urgency and computational requirements: critical real-time processing at edge devices for immediate safety responses, near-real-time aggregation at intermediate servers, and batch processing for comprehensive analysis at cloud resources. This segmentation enables time-sensitive operations to proceed locally without consuming valuable bandwidth.
Solution Approach 2:
Different processing qualities are applied at different locations based on local requirements. Edge computing devices provide high-quality real-time processing for critical safety functions where immediate response is essential. Intermediate servers provide moderate-quality near-real-time processing for regional coordination. Cloud resources provide comprehensive analysis quality for non-time-critical insights. This local quality differentiation optimizes bandwidth usage while maintaining appropriate response times for each operational context.
Data Source
AI summary
The present disclosure provide multi-access edge computing systems and methods. One such system comprises a plurality of sensor devices that are configured to collect construction site sensor data and transmit the sensor data to a local computing system that is configured to combine the sensor data with user feedback data and transmit the combined data to an edge computing system. The edge computing system is configured to process the combined data and transmit the combined data to a cloud computing system, where the cloud computing system that is configured to process the transmitted data from the edge computing system. The edge computing system or the cloud computing system is configured to execute a site risk prediction application and predict a hazard within a construction site based on the collected construction site sensor data and generate an output signal to equipment operating at the construction site.