Dynamic Resource Provisioning via Demand Curves
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional techniques often fail to dynamically adjust computing resources to match fluctuating user demands, leading to uncoupled cloud performance and cost effectiveness, resulting in either sluggish performance or high costs due to inadequate or excessive resource provisioning.
Innovation Solution
A control system manages dynamic provisioning of computing resources by converting triggers into demand curves and maintaining a dynamic provisioning profile, which specifies resource allocation and de-allocation thresholds, allowing for gradual and adaptive resource provisioning based on user-defined attack and release rates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If computing resources are provisioned to meet peak demand, then performance is improved, but cost increases
Solution Approach 1:
The patent implements dynamic resource provisioning that automatically adjusts computing resources based on real-time demand fluctuations. The system monitors traffic patterns and dynamically scales resources up during peak periods and down during lulls, ensuring performance requirements are met while optimizing cost by preventing payment for idle capacity.
Solution Approach 2:
The system employs feedback mechanisms by continuously monitoring demand signals and using this information to adjust resource provisioning decisions. The feedback loop enables the system to respond to changing conditions in real-time, balancing performance needs against cost considerations through automated adjustments based on observed demand patterns.
2Loss of energy
If computing resources are reduced to lower cost, then cost effectiveness is improved, but performance deteriorates
Solution Approach 1:
The system dynamically adjusts resource levels based on actual demand, preventing both over-provisioning and under-provisioning. By continuously adapting resource allocation to match current workload requirements, the system maintains adequate performance while minimizing costs, avoiding the static limitations of conventional fixed provisioning approaches.
Solution Approach 2:
The system performs preliminary actions by pre-configuring resource provisioning strategies and demand curve calculations in advance. This allows the system to be prepared for demand fluctuations and execute appropriate provisioning decisions quickly when demand changes occur, ensuring performance is maintained while optimizing cost effectiveness.
3Speed
If resources are rapidly provisioned to meet sudden demand, then responsiveness is improved, but system stability deteriorates
Solution Approach 1:
The system implements periodic action through demand curve calculations that spread resource provisioning over time rather than executing instantaneous changes. By calculating and executing resource adjustments in controlled intervals based on demand patterns, the system maintains responsiveness to demand changes while preventing sudden spikes that could destabilize the system.
Solution Approach 2:
The system applies beforehand cushioning by preparing resource provisioning strategies in advance and using pre-calculated demand curves to guide resource allocation. This cushioning effect buffers against sudden demand fluctuations, allowing the system to respond quickly while maintaining stability through pre-planned adjustment mechanisms rather than reactive scrambling.
Data Source
AI summary
Computing resources are dynamically provisioned to virtual and physical systems. In one embodiment, a control system manages the provisioning of computing resources for multiple client systems. A request for resource provisioning can be sent to the control system as a trigger. The control system converts the information in the trigger into a demand curve that specifies the rates at which resources are to be provided to a client system. The control system then causes the resources to be provisioned to the client system based on the demand curve and a dynamic provisioning profile. The dynamic provisioning profile can be created by a system administrator based on the amount and characteristics of the resources available for provisioning the client system. The dynamic provisioning profile can also specify one or more gate points that indicate the thresholds at which dynamic provisioning can be stopped.