Brownout Prevention via Predictive Throttling in Mobile Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile devices face challenges in proactive thermal management and brownout prevention, particularly in high-power use cases like 5G mmWave technologies, where reactive throttling processes can lead to unexpected shutdowns and on-chip temperature sensors consume valuable chip space.
Innovation Solution
A brownout prediction-based throttling management system that uses a processor with a brownout predictor, throttling manager, chip temperature estimator, and voltage drop detector to implement a time-based reverse order throttling scheme, estimating chip temperature and detecting supply voltage drops without dedicated temperature sensors, thereby preventing brownouts proactively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If reactive throttling processes are used to manage thermal issues, then thermal management is implemented, but brownouts occur due to unexpected shutdowns from sudden increased power consumption
Solution Approach 1:
The system performs preliminary actions by predicting potential brownout scenarios before they occur. The processor monitors power consumption patterns and predicts when voltage drops may cause brownouts, allowing the throttling manager to proactively reduce power consumption in advance rather than reacting after the brownout has occurred.
Solution Approach 2:
The system implements feedback mechanisms where the processor continuously monitors power consumption, voltage levels, and thermal conditions. This feedback loop allows the system to adjust throttling levels dynamically based on real-time conditions, preventing brownouts while optimizing performance.
2Reliability
If on-chip temperature sensors are included to monitor thermal conditions, then thermal management is improved, but valuable chip space is consumed that could be used for other processing resources
Solution Approach 1:
The system extracts the temperature sensing function from dedicated on-chip temperature sensors. Instead of relying solely on traditional temperature sensors that consume chip space, the patent uses alternative methods such as monitoring voltage drops, current consumption patterns, and thermal models to infer temperature conditions, thereby eliminating the need for dedicated sensor hardware.
Solution Approach 2:
The system makes existing components multi-functional by using voltage drop detection and power consumption monitoring for both power management and thermal management purposes. This universal approach allows a single monitoring mechanism to serve multiple functions, eliminating the need for separate dedicated temperature sensors.
3Adaptability or versatility
If 5G mmWave technologies are implemented to enhance mobile wireless communication, then communication capabilities are improved, but power and thermal boundaries are pushed causing brownout risks
Solution Approach 1:
The system implements dynamic power management that adapts to varying communication demands. The throttling manager dynamically adjusts power consumption levels based on real-time monitoring of power usage patterns, voltage levels, and thermal conditions, allowing the system to maintain stable power delivery while supporting 5G mmWave communication capabilities.
Solution Approach 2:
The system changes operational parameters such as data throughput, processing frequency, and power consumption levels to prevent brownouts. By monitoring voltage drops and power consumption patterns, the system adjusts these parameters proactively to maintain stable power delivery even under high-demand 5G mmWave communication conditions.
Data Source
AI summary
In one embodiment, an apparatus of a mobile device includes memory comprising instructions and processing circuitry coupled to the memory to implement the instructions to: process messages from a network device indicating a scheduling of network traffic for the mobile device, determine an estimated peak power consumption associated with the scheduling of network traffic based on the messages, and execute a time-based throttling scheme for a modem of the mobile device based on the estimated peak power consumption.