Safety-Aware Task Orchestration Across Cloud, Edge, and Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Static distribution of safety awareness tasks across computing environments leads to underutilization of resources, excessive costs due to worst-case configurations, and inflexibility in upgrading or adding safety-critical services without upgrading dedicated hardware and software resources.
Innovation Solution
Dynamic provisioning and distribution of safety-critical services across the compute continuum using a safety-aware orchestrator, which creates multiple safety assurance profiles to leverage diverse resources, allowing for flexible assignment of tasks across cloud, edge, and device nodes, thereby optimizing resource utilization and reducing costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If safety-critical services are distributed statically across computing environments, then safety assurance is maintained through dedicated resources, but resource utilization is underutilized and costs increase
Solution Approach 1:
The patent implements dynamic task distribution where safety-aware orchestrators continuously monitor resource availability and safety requirements across cloud, edge, and device nodes. Tasks are dynamically assigned to appropriate nodes based on real-time conditions rather than static pre-assignment, enabling both high safety assurance through verified node selection and high resource utilization through flexible load balancing across the compute continuum.
Solution Approach 2:
The patent creates a unified compute continuum that integrates cloud, edge, and device resources into a single pool that can serve multiple safety-critical services. Instead of dedicating separate hardware resources to each service, the system allows any node in the continuum to perform safety-critical tasks when conditions permit, making resources universal and multi-functional while maintaining safety through orchestrator verification.
2Reliability
If dedicated hardware resources are reserved for safety-critical services, then safety assurance is guaranteed, but system flexibility and upgrading capability are reduced
Solution Approach 1:
The system dynamically determines which nodes can perform safety-critical tasks based on real-time verification of safety mechanisms and resource availability. This dynamic approach replaces static hardware reservations, allowing the system to adapt to changing conditions and upgrade services by simply reconfiguring task assignments through orchestrators without physical hardware changes.
Solution Approach 2:
The patent uses virtualization to create virtual instances of safety-critical services that can be deployed across multiple physical nodes in the compute continuum. Instead of binding a service to dedicated hardware, virtual copies can be instantiated on any node that meets safety requirements, enabling flexible service upgrading and migration without hardware constraints.
3Reliability
If safety-critical tasks are assigned to expensive dedicated resources, then reliability is improved, but cost efficiency deteriorates
Solution Approach 1:
The patent implements a tiered approach where not all safety-critical tasks require the highest level of dedicated resources at all times. The orchestrator assesses each task's specific safety requirements and assigns it to the minimum necessary resource level that can satisfy those requirements. This partial action principle allows lower-cost resources to handle tasks when conditions permit, reducing overall cost while maintaining adequate safety assurance.
Solution Approach 2:
The system dynamically changes resource allocation parameters based on task characteristics, current system state, and safety requirements. Instead of always allocating expensive dedicated resources, the orchestrator adjusts allocation parameters in real-time to match the actual needs of each task, optimizing the balance between safety assurance and cost efficiency across the compute continuum.
Data Source
Figure 1A
Figure 1B
Figure 2
AI summary
Disclosed herein are systems and methods for dynamically distributing a safety awareness task. The systems and methods may include receiving hardware resources data associated with a plurality of remote computing systems. A plurality of safety assurance profiles may be received. Each of the plurality of safety assurance profiles may be associated with a respective service. A safety assurance task may be dynamically assigned to one of the plurality of remote computing systems based on the hardware resources data and one of the plurality of safety assurance profiles.