Transcoding Service Bidding for Excess Cloud Resource Utilization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems for managing media processing in multi-tenant computing environments, such as cloud computing, face inefficiencies in utilizing resource capacity, leading to excess capacity in one type while others are fully utilized, resulting in high costs and resource wastage.
Innovation Solution
A transcoding service that utilizes excess capacity of computing resources by allowing users to bid for unused resources, optimizing transcoding processes based on dynamically changing market prices, and suspending or resuming tasks when prices exceed the customer's bid, thereby efficiently utilizing resources and reducing costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If dedicated resources are provided to users in multi-tenant computing environments, then reliability and service level are improved, but cost and resource wastage increase due to excess capacity
Solution Approach 1:
The patent merges excess capacity from dedicated resources with on-demand resource pools, allowing both dedicated and on-demand workloads to share the same physical infrastructure. This combining approach enables dedicated resources to serve multiple users while maintaining service level guarantees, eliminating resource wastage while preserving reliability.
Solution Approach 2:
The system implements a universal resource allocation mechanism where dedicated resources can serve multiple users simultaneously based on bid prices. The resource allocation server treats all users uniformly regardless of their dedicated or on-demand status, allowing a single resource to fulfill multiple functions for different users while optimizing cost efficiency.
2Productivity
If additional capacity is purchased to handle peak demand, then productivity is improved, but cost increases due to unused excess capacity during low demand periods
Solution Approach 1:
The patent implements dynamic resource allocation where the system automatically adjusts resource assignment based on real-time demand and bid prices. During peak demand, additional capacity is dynamically allocated from the on-demand pool to dedicated resources. During low demand periods, the system dynamically reassigns resources to maximize utilization, preventing cost waste while maintaining productivity capability.
Solution Approach 2:
The system changes the allocation parameters of resources based on demand conditions and bid prices. The resource allocation server modifies allocation decisions by considering factors such as bid price, demand level, and resource availability, allowing the system to optimize the balance between productivity and cost efficiency under varying conditions.
3Ease of operation
If conventional resource allocation systems are used, then ease of operation is maintained, but productivity decreases due to inefficient resource utilization with excess capacity in one type while others are fully utilized
Solution Approach 1:
The patent implements a feedback mechanism where the resource allocation server continuously monitors resource usage, bid prices, and demand conditions. Based on this feedback, the system automatically adjusts resource allocation decisions to optimize utilization efficiency. The feedback loop enables the system to respond to changing conditions and correct inefficiencies without requiring manual intervention, maintaining ease of operation while improving productivity.
Data Source
AI summary
A transcoding service is described that is capable of utilizing the excess capacity of the computing resources of a service provider. The customer of the transcoding service can submit a bid price for completing the transcodes. As long as the specified price exceeds the fluctuating price of the unused resource instances, the transcoding service will execute the job on the unused instance(s). If the price of the unused resource instances exceeds the customer's bid, the transcoding process stops. The transcoding service may pause the transcoding when the dynamically fluctuating price of the unused resource exceeds the customer's bid and then resume when the price falls back down. Users can specify constraints for transcoding, such as timeframes during which the transcode must be completed, a total price for completing transcoding or priorities of the media files. The system can automatically optimize the utilization of the resource instances according to the constraints.