Edge Storage Management Balancing IoT Data Access and Capacity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The accumulation of large amounts of IoT data in edge servers leads to storage capacity issues, as edge servers are small-scale cloud data centers that directly communicate with user terminals, and there is a concern that their storage capacity may become tight.
Innovation Solution
A storage management apparatus that acquires access log information from edge servers, decides on a sensor-by-sensor basis whether data access meets a preset criterion, and transfers data failing to meet the criterion to another storage part, such as another edge server or a cloud server, based on access frequency and elapsed time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If edge servers store large amounts of IoT data locally, then data access speed is improved, but storage capacity becomes tight
Solution Approach 1:
The patent segments storage resources across multiple edge servers and cloud storage, dividing the storage burden. Each edge server maintains only frequently accessed data locally, while less accessed data is segmented and stored in cloud storage or transferred to other edge servers with available capacity.
Solution Approach 2:
The patent introduces a new dimension of storage by utilizing cloud storage and inter-edge-server transfer capabilities. This creates a multi-layered storage architecture where data can be moved between local edge storage, other edge servers, and cloud storage, effectively expanding storage capacity beyond individual server limitations.
2Quantity of substance
If data is transferred from edge servers to cloud storage, then storage capacity is freed, but access delay increases
Solution Approach 1:
The patent applies local quality by maintaining frequently accessed data locally at edge servers while transferring less accessed data to cloud storage. The system dynamically determines which data should remain local based on access patterns, ensuring that data requiring fast access stays in the local environment while freeing storage capacity for other uses.
Solution Approach 2:
The patent implements feedback mechanisms that monitor data access patterns and automatically adjust storage locations. When data access frequency changes, the system receives feedback and repositions data accordingly - moving frequently accessed data back to edge servers and transferring less accessed data to cloud storage, thereby optimizing the balance between access speed and storage capacity.
3Device complexity
If all IoT data is stored at centralized cloud, then storage management is simplified, but propagation delay increases
Solution Approach 1:
The patent segments the centralized storage model into distributed edge storage nodes. Instead of all data residing at a single centralized cloud location, data is segmented and distributed across multiple edge servers positioned geographically closer to data sources and users, reducing propagation delay while maintaining manageable storage through coordinated management.
Solution Approach 2:
The patent introduces edge servers as intermediary storage nodes between IoT data sources and the centralized cloud. These intermediaries store data locally to reduce access delay, while a storage management device coordinates data placement and movement between intermediaries and the central cloud, maintaining simplified management architecture.
4Quantity of substance
If edge servers maintain large storage capacity, then more data can be cached locally, but system cost increases
Solution Approach 1:
The patent merges storage resources across multiple edge servers and combines them with cloud storage capacity. Instead of each edge server independently maintaining large storage capacity, the system combines available storage from multiple servers and cloud resources to provide equivalent total capacity, reducing the need for expensive high-capacity storage at each individual edge server.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
In a system using edge computing, a technology for performing efficient storage management is provided. A storage management apparatus communicable with a plurality of edge servers each including a storage part storing data and access log information to the data is configured to acquire the access log information from each edge server; to decide, based on the acquired access log information, whether a state of access to the data stored in the storage part of each edge server meets a preset criterion; and to execute control to select, as a transfer target, data in the state of access which is decided as failing to meet the criterion, and to transfer the data to another storage part different from the storage part in which the data is stored.