Cloudlet Agent Information Sharing for Distributed Resource Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In large cloud environments, maintaining up-to-date information about service attributes of cloudlets is resource-intensive and can lead to performance bottlenecks, as well as being a single point of failure, making it difficult to find suitable resources for workload scheduling.
Innovation Solution
A decentralized approach where each cloudlet agent shares information about service properties with neighboring agents, forming groups based on criteria such as geographical location and service properties, allowing for efficient comparison and updating of available resources without relying on a central database.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If a central database is used to maintain up-to-date information about all cloudlets, then information availability is improved, but system complexity and resource consumption increase significantly
Solution Approach 1:
The patent divides the centralized information management system into distributed segments. Each cloudlet maintains its own service attribute information locally, and information is segmented across multiple cloudlet agents rather than concentrated in a single central database. This segmentation reduces the complexity burden on any single component while maintaining overall information availability.
Solution Approach 2:
The patent introduces cloudlet agents as intermediary components that facilitate information sharing between cloudlets. These agents act as mediators that collect, store, and exchange service attribute information locally, eliminating the need for a complex central database while ensuring information is available when needed for workload scheduling.
2Loss of information
If a central database is used to store all cloudlet information, then information completeness is improved, but performance bottlenecks occur due to query overhead
Solution Approach 1:
The patent segments the information storage function across multiple distributed cloudlet agents rather than using a single centralized storage system. Each agent stores information about cloudlets in its local vicinity, enabling parallel query processing and eliminating the performance bottleneck associated with centralized database queries.
Solution Approach 2:
The patent implements local quality by having each cloudlet agent maintain information about nearby cloudlets in its local environment. This local caching strategy ensures that frequently accessed information is available locally without requiring remote database queries, thereby improving query performance while maintaining information completeness through the distributed network of agents.
3Loss of information
If a central database is used to manage cloudlet information, then information centralization is improved, but system reliability decreases due to single point of failure
Solution Approach 1:
The patent segments the information management function across multiple independent cloudlet agents distributed throughout the cloud network. This segmentation eliminates the single point of failure inherent in centralized databases, as the failure of any single agent does not compromise the overall system's ability to provide information for workload scheduling.
Solution Approach 2:
The patent introduces cloudlet agents as intermediary components that distribute information management responsibilities across the network. These agents act as redundant intermediaries, ensuring that information remains accessible even if some agents fail, thereby improving system reliability while maintaining the benefits of centralized information availability.
4Loss of information
If all cloudlet information is maintained centrally, then information accessibility is improved, but resource consumption increases significantly
Solution Approach 1:
The patent segments the information storage and management burden across multiple distributed cloudlet agents rather than concentrating it in a single central system. Each agent maintains a portion of the information locally, reducing the overall resource consumption required to maintain and access cloudlet information while ensuring it remains accessible for workload scheduling decisions.
Solution Approach 2:
The patent implements local quality by having each cloudlet agent maintain information about local cloudlets in its vicinity. This local caching approach ensures that information remains highly accessible for nearby workloads while significantly reducing the resource consumption associated with maintaining and accessing a large centralized database across the entire cloud network.
Data Source
AI summary
It is disclosed an agent of a first cloudlet and a method performed therein, the first cloudlet having one or more service properties, the first agent having associated a first group of one or more other cloudlets. Based on an exchange of information about service properties of cloudlets accessible to each agent, a comparison is made between service properties from different cloudlets, and if a certain cloudlet has at least one service property that exceeds a service property of any one of the first group of cloudlets, the certain cloudlet is added to a group of cloudlets, which efficiently represents service properties available to the first agent.