18156541. Access Pattern Driven Data Placement in Cloud Storage simplified abstract (GOOGLE LLC)
Contents
Access Pattern Driven Data Placement in Cloud Storage
Organization Name
Inventor(s)
Wangyuan Zhang of Fremont CA (US)
Vivienne Zhang of Santa Clara CA (US)
Pramod Gaud of San Jose CA (US)
Sangho Yoon of Palo Alto CA (US)
Xudong Shi of Sunnyvale CA (US)
Saifeng Yao of Fremont CA (US)
Access Pattern Driven Data Placement in Cloud Storage - A simplified explanation of the abstract
This abstract first appeared for US patent application 18156541 titled 'Access Pattern Driven Data Placement in Cloud Storage
Simplified Explanation
The abstract describes a system and method for storing data in a distributed network with multiple datacenters spread across different geographic regions. Here is a simplified explanation of the patent application:
- Data is received and uploaded to a first datacenter in the distributed network.
- Access information about previously stored data in the network is also received.
- Based on the metadata (information about the uploaded data) and the access information, the system predicts the geographic regions from which the uploaded data will be accessed.
- The uploaded data is then instructed to be transferred from the first datacenter to one or more second datacenters located in each of the predicted geographic regions.
Potential applications of this technology:
- Cloud storage: The system can be used by cloud storage providers to efficiently distribute data across multiple datacenters based on user access patterns.
- Content delivery networks (CDNs): CDNs can utilize this system to store and deliver content closer to end-users, reducing latency and improving performance.
- Disaster recovery: By storing data in multiple geographic regions, the system can provide redundancy and ensure data availability in the event of a datacenter failure or natural disaster.
Problems solved by this technology:
- Efficient data distribution: The system optimizes the storage and transfer of data by predicting the regions where the data will be accessed, reducing the need for unnecessary data replication.
- Improved data availability: By distributing data across multiple datacenters, the system enhances data availability and resilience, minimizing the risk of data loss or service disruption.
- Reduced latency: Storing data closer to end-users in their respective regions reduces network latency, resulting in faster access to the data.
Benefits of this technology:
- Scalability: The distributed network architecture allows for easy scaling of storage capacity by adding more datacenters in different regions.
- Cost-effectiveness: By intelligently distributing data, the system optimizes resource utilization and reduces infrastructure costs.
- Enhanced performance: Predicting and transferring data to the regions where it will be accessed improves overall system performance and user experience.
Original Abstract Submitted
A system and method for storing data in a distributed network having a plurality of datacenters distributed over a plurality of geographic regions. The method may involve receiving data, including metadata, uploaded to a first datacenter of the distributed network, receiving access information about previous data that was previously stored in the plurality of datacenters of the distributed network, predicting one or more of the plurality of geographic regions from which the uploaded data will be accessed based on the metadata and the access information, and instructing the uploaded data to be transferred from the first datacenter to one or more second datacenters located at each of the one or more predicted geographic regions.
