Concurrent Network Scheduling for Mobile Power Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Portable computing devices face reduced battery life due to increased power consumption from using bandwidth-intensive network applications, particularly with wireless network radios.
Innovation Solution
Implementing a system for concurrent network application scheduling, where mobile computing devices delay non-essential network requests to execute them alongside essential ones, reducing overall power consumption without adversely affecting application performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If network requests are executed sequentially, then power consumption is higher, but application performance may be adversely affected
Solution Approach 1:
The system performs preliminary classification of network requests into delayable and non-delayable categories before execution. By identifying which requests can be postponed in advance, the system can batch them with other delayable requests for concurrent execution, thereby reducing power consumption while ensuring that non-delayable requests are handled promptly to maintain application performance.
Solution Approach 2:
The system dynamically adjusts the execution strategy based on request characteristics. It flexibly switches between sequential execution (for non-delayable requests requiring immediate handling) and concurrent execution (for delayable requests that can be batched), optimizing the balance between power consumption and application performance in real-time.
2Use of energy by moving object
If network requests are executed concurrently, then power consumption is reduced, but request scheduling complexity increases
Solution Approach 1:
The system segments network requests into distinct categories: delayable requests and non-delayable requests. This segmentation simplifies the scheduling complexity by applying different execution strategies to different segments - delayable requests are batched for concurrent execution to save power, while non-delayable requests are handled immediately, avoiding the need for complex scheduling decisions across all request types.
3Use of energy by moving object
If network requests are delayed for concurrent execution, then power consumption is reduced, but execution time may increase
Solution Approach 1:
The system performs preliminary classification to identify delayable requests before they enter the execution queue. By knowing in advance which requests can be postponed, the system can efficiently batch them with other delayable requests for concurrent execution, reducing the total execution time compared to sequential processing, while still achieving power consumption reductions through strategic delay.
Data Source
AI summary
Technologies for scheduling network requests to reduce power consumption include a mobile computing device configured to receive a network request from a network application, and determine whether the network request is delayable, based on execution constraints of the application. Execution constraints may include required processing resources, acceptable latency, priority, application class, and others. If the request is delayable, the mobile computing device may delay the request until a threshold number of delayable requests are received, or until a non-delayable request is received. The mobile computing device performs the delayed request and any subsequently received requests concurrently. The execution constraints may be supplied by each network application, or may be determined by the mobile computing device through observation. Other embodiments are described and claimed.