Distributed Power Budget Controllers for Thermal Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Centralized power and thermal management in computer systems faces challenges when devices suddenly increase power consumption, leading to processing load imbalances and potential failures, particularly in distributed systems where sudden changes can exceed power limits.
Innovation Solution
A distributed system with component controllers and a service processor that computes local power budgets and detects failures, allowing for reset of faulty components without interrupting operations, and transitions to safe mode to manage power and thermal thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If centralized power management is implemented, then power and thermal management can be coordinated across devices, but processing load on the management entity increases when devices suddenly increase power consumption
Solution Approach 1:
The patent divides the centralized power management entity into multiple distributed component controllers, each responsible for managing power consumption of specific devices. This segmentation distributes the processing load across multiple independent controllers, preventing any single entity from becoming a bottleneck when devices suddenly increase power consumption, while maintaining coordinated power management across the system.
2Productivity
If distributed control is implemented, then processing load is reduced on management entities, but system complexity increases due to multiple controllers
Solution Approach 1:
The patent combines multiple component controllers into a unified distributed control architecture where each controller manages specific devices but they all participate in a coordinated system. The service processor merges the functions of monitoring and coordinating these distributed controllers, allowing the system to achieve both reduced processing load on individual entities and simplified overall management through centralized oversight of the distributed components.
3Ease of operation
If reset threshold is not exceeded, then faulty controller can be reset without interrupting operations, but system reliability may be compromised if failure is not properly handled
Solution Approach 1:
The patent implements a feedback mechanism where the service processor continuously monitors component controllers and detects failures. When a failure is detected, the service processor evaluates whether the reset threshold has been exceeded and determines the appropriate recovery action. This feedback loop ensures that faulty controllers are reset appropriately without interrupting operations when safe, while maintaining system reliability through proper failure handling and threshold-based decision making.
Data Source
AI summary
An apparatus includes a plurality of components and a plurality of component controllers. Each of the plurality of component controllers is associated with at least one component of the plurality of components. Each component controller is configured to compute a local power budget for the at least one component based, at least in part, on the power differential and the proportion of the total power consumption corresponding to the at least one component. A service processor is configured to determine failure associated with at least one component controller of the plurality of component controllers or the at least one component associated with the at least one component controller. The service processor is configured to in response to a reset threshold not being exceeded, reset the at least one component controller without interrupting operations of any components of the at least one component that have not failed.