Compute Power Budget Control for Thermal-Limited Mobile Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing power management techniques in mobile computing devices fail to effectively manage thermal energy and power consumption, leading to potential damage from excessive heat and battery discharge issues.
Innovation Solution
Implementing a feedback loop with system-level power measurements to dynamically adjust performance and limit maximum average power consumption by calculating a power budget threshold based on digital power meters and actuators, using a power limits driver to balance power between components like CPU and GPU.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If dynamic power adjustment techniques are used to maximize battery time and control thermal energy, then power consumption is reduced, but the ability to limit maximum average power consumption effectively is insufficient
Solution Approach 1:
The patent implements a feedback mechanism where power consumption is continuously monitored and used to dynamically adjust performance states. The system measures actual power consumption, compares it against thresholds, and adjusts compute device performance accordingly to maintain operation within thermal and power constraints while maximizing battery life.
Solution Approach 2:
The system dynamically adjusts performance states of compute devices based on real-time power consumption measurements and thermal conditions. Rather than static power management, the system continuously adapts performance levels to balance power consumption, thermal management, and computational requirements.
2Productivity
If compute devices operate at high workload levels to maintain performance, then productivity is improved, but thermal energy generation increases causing potential damage to internal circuitry
Solution Approach 1:
The system employs periodic monitoring of power consumption and thermal conditions, adjusting performance in cycles rather than continuously. Power consumption is measured over defined periods, and performance states are adjusted periodically to maintain productivity while preventing thermal damage accumulation.
Solution Approach 2:
The system changes operational parameters of compute devices based on measured power consumption and thermal conditions. By adjusting voltage, frequency, and performance states dynamically, the system maintains high productivity when conditions permit while preventing thermal damage when power consumption exceeds safe thresholds.
3Measurement precision
If system-level power measurements are implemented to calculate power budget thresholds, then power control precision is improved, but device complexity increases
Solution Approach 1:
The patent implements a universal power management approach where a single power management entity handles multiple compute devices and various power constraints. This multi-functional system calculates power budget thresholds for different devices and scenarios using standardized measurements and procedures, reducing overall system complexity despite enhanced measurement precision.
Solution Approach 2:
The power management system is segmented into distinct functional components: power measurement modules for each compute device, a central power budget calculation entity, and performance control modules. This segmentation allows precise measurement at each level while managing complexity through modular architecture and clear separation of concerns.
Data Source
AI summary
A method for power control includes receiving first power consumption data of a first compute device based on measurements of the first compute device, and receiving second power consumption data of a second compute device based on measurements of the second compute device. The method further includes receiving system power data to obtain a system power limitation. The method also includes calculating a power budget threshold for the first compute device and the second compute device based on the first power consumption data, the second power consumption data, and the system power limitation. The method includes controlling performance of the first compute device to operate within the power budget threshold, and controlling performance of the second compute device to operate within the power budget threshold.