Predictive Streaming System for Mobile Storage Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile devices face storage constraints due to large applications and games, leading to performance delays and storage inefficiencies, as existing solutions fail to effectively manage storage between local and cloud-based systems.
Innovation Solution
The App Streamer framework predicts data block usage patterns and prefetches necessary blocks from cloud storage, balancing storage usage and bandwidth consumption to minimize application startup delays, using a machine learning-based approach that groups blocks into superblocks for reduced computational and memory overhead.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If large applications and games are stored locally on mobile devices, then application performance and user experience are improved, but storage capacity is consumed and storage constraints are exacerbated
Solution Approach 1:
The patent segments application data into blocks and groups them into superblocks based on access patterns. Only essential blocks are cached locally while the rest remain in cloud storage, allowing fast access to frequently used data without storing the entire application locally.
Solution Approach 2:
The system performs preliminary actions by predicting which data blocks will be needed and pre-fetches them from cloud storage before they are actually accessed. This predictive caching ensures data is ready when needed without requiring full application storage.
2Speed
If all application data is stored locally, then access speed is maximized, but storage management complexity increases and storage efficiency decreases
Solution Approach 1:
The system implements self-service by automatically monitoring data access patterns, predicting future needs, and managing cache contents without user intervention. The machine learning model autonomously determines which blocks to prefetch and when to evict them from local storage.
Solution Approach 2:
The patent changes the parameter of data organization from individual blocks to superblocks grouped by access patterns. This parameter change simplifies storage management by reducing the number of individual data items that need to be tracked and managed separately.
3Loss of time
If predictive prefetching is implemented, then application startup delays are reduced, but bandwidth consumption increases
Solution Approach 1:
The system applies partial action by prefetching only the necessary data blocks predicted to be needed, rather than downloading entire applications. The machine learning model determines the minimum sufficient set of blocks to prefetch, avoiding excessive bandwidth consumption while still reducing startup delays.
Solution Approach 2:
The system uses feedback from actual data access patterns to refine its predictions. By continuously monitoring which blocks are accessed and how long they remain in cache, the system adjusts its prefetching strategy to reduce unnecessary bandwidth consumption while maintaining performance benefits.
Data Source
AI summary
System and methods for predictive application streaming are provided. The system may execute an application and, concurrently, the system may while load data blocks not stored on the device using a construct of superblocks. The system may detect an access event caused by an application accessing a data block in a memory. The system may determine, in response to the access event, a superblock comprising a plurality of blocks that are historically accessed within the same execution time window as the block. The system may forecast, based on the superblock and a machine learning model, superblocks to be accessed by the application that are not stored in the memory. The system may download the superblocks from a remote endpoint accessible via a network.