Cloud Resource Allocation via Dedicated Hardware Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a need for a solution that enables identification and provision of on-demand computing resources in response to real-time demand at predictable pricing, and with a lower risk of forced deallocation during peak demand scenarios in cloud computing platforms.
Innovation Solution
The solution involves a computer-implemented method and system for resource management in on-demand cloud computing platforms. It includes receiving a request for access to cloud computing resources, parsing data records to identify available resources, matching resource attributes, retrieving access control credentials, and delivering cloud computing services by instantiating virtual machine processes on matched hardware devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If spot instances are used to reduce pricing, then cost is reduced, but reliability deteriorates due to forced deallocation risk
Solution Approach 1:
The system performs preliminary actions by pre-identifying and pre-reserving dedicated hardware devices before peak demand occurs. The resource sharing platform maintains inventory records of dedicated devices and proactively allocates them to requests that match available resources, preventing the need for spot instances and their associated deallocation risks.
Solution Approach 2:
The resource sharing platform acts as an intermediary between dedicated capacity resource users and on-demand resource requests. It manages the inventory of dedicated devices and facilitates fair sharing during peak demand, eliminating the need for users to directly face spot instance deallocation risks while maintaining cost efficiency.
2Reliability
If dedicated capacity is reserved for exclusive use, then reliability is improved, but device complexity increases due to resource allocation constraints
Solution Approach 1:
The system makes dedicated hardware devices universal by allowing them to serve multiple purposes through shared access during peak demand. The resource sharing platform enables dedicated devices to be allocated to different users based on real-time availability and request matching, eliminating the need for complex exclusive allocation mechanisms while maintaining reliability.
Solution Approach 2:
The system introduces dynamics to dedicated resource allocation by allowing real-time changes in device availability status. The resource sharing platform continuously updates inventory records and dynamically adjusts allocations based on peak demand conditions, transforming static exclusive reservations into flexible dynamic sharing without increasing operational complexity.
3Productivity
If real-time demand is met with available resources, then productivity is improved, but loss of substance increases due to higher per-unit pricing
Solution Approach 1:
The system changes the parameter of resource availability by maintaining an inventory of dedicated devices with known availability status. The resource sharing platform uses this updated information to match real-time requests with available dedicated resources, enabling productive allocation without the high per-unit pricing associated with spot instances, as dedicated resources are allocated based on fair sharing principles rather than market volatility.
Data Source
AI summary
The present invention relates to on-demand cloud computing. The invention includes (i) receiving a request for providing a first resource user access to a first set of cloud computing devices (ii) parsing data records corresponding to a second set of cloud computing devices. Each device within the second set of cloud computing devices is reserved for exclusive use by a dedicated capacity resource user, (iii) identifying a matched set of cloud computing devices that is a sub-set of the second set of cloud computing devices. Hardware resource attributes of the matched set of cloud computing devices match hardware resource attributes identified in the received request, (iv) retrieving access control credentials associated with each hardware device within the matched set of cloud computing devices, and (v) delivering a cloud computing service to the first resource user through the matched set of cloud computing devices.


