Dynamic Advance Reservation Scheduling for Grid Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data transmission scheduling methods in Grid networks face inefficiencies due to resource fragmentation and high blocking probabilities, particularly in advance reservation systems, where preallocation of channels leads to suboptimal utilization of bandwidth and increased blocking rates.
Innovation Solution
The Single Slot Advance Reservation (SSAR) method introduces a two-phase process: a request provisioning phase that checks availability without allocation, followed by a request allocation phase that optimizes channel and path allocation at the time of data transmission, avoiding preallocation and thus reducing resource fragmentation and blocking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If advance reservation methods preallocate channels for future data transmission, then resource availability is guaranteed, but resource fragmentation increases and bandwidth utilization deteriorates
Solution Approach 1:
The system performs preliminary provisioning of advance reservation requests without actual channel allocation. The request is recorded and validated for future feasibility, but resources are not committed until the allocation phase near the transmission time, preventing premature resource fragmentation while ensuring resource availability through advance planning
Solution Approach 2:
The system transitions from static preallocation to dynamic delayed allocation. Channel assignment is postponed until closer to the transmission time when actual network conditions are known, allowing flexible adaptation to changing traffic patterns and improving bandwidth utilization while maintaining reliability through the two-phase approach
2Reliability
If traditional ASAR methods allocate channels in advance, then blocking probability is reduced, but scheduler complexity and signaling overhead increase
Solution Approach 1:
The scheduling process is segmented into two distinct phases: provisioning phase (advance reservation request handling) and allocation phase (channel assignment near transmission time). This segmentation reduces scheduler complexity by separating long-term planning from short-term resource management, while maintaining low blocking probability through coordinated execution of both phases
Solution Approach 2:
The complex channel allocation decision-making is extracted from the advance reservation phase and postponed to the allocation phase. Only simple request validation and recording are performed during provisioning, while detailed channel assignment is deferred to when transmission is imminent, reducing signaling overhead and scheduler complexity
3Reliability
If channels are preallocated for advance reservation requests, then transmission reliability is improved, but resource fragmentation increases
Solution Approach 1:
The system performs preliminary validation and recording of advance reservation requests without actual channel allocation. Resources are reserved in the sense that the request is acknowledged and scheduled, but physical channel assignment is delayed until the allocation phase, preventing resource fragmentation while maintaining transmission reliability through the two-phase approach
Solution Approach 2:
The system changes the temporal parameter of channel allocation from immediate (at reservation time) to delayed (near transmission time). This parameter change allows the network to maintain resource flexibility and reduce fragmentation while still guaranteeing transmission reliability through the structured provisioning and allocation phases
Data Source
AI summary
A method of scheduling data transmissions from a source to a destination, includes the steps of: providing a communication system having a number of channels and a number of paths, each of the channels having a plurality of designated time slots; receiving two or more data transmission requests; provisioning the transmission of the data; receiving data corresponding to at least one of the two or more data transmission requests; waiting until an earliest requested start time Ts; allocating at the current time each of the two or more data transmission requests; transmitting the data; and repeating the steps of waiting, allocating, and transmitting until each of the two or more data transmission requests that have been provisioned for a transmission of data is satisfied. A system to perform the method of scheduling data transmissions is also described.