Elastic Network Bandwidth Scheduling for Data Transfer Cost Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current bandwidth provisioning methods result in over-provisioning and excess costs due to peak demand occurring infrequently, and attempts to reduce bandwidth often lead to expensive overcharges during peak usage in large data center applications like data mirroring or backup, where massive data transfers are common.
Innovation Solution
A computer-implemented method that maintains multiple bandwidth optimization criteria for different data transfer event scenarios, dynamically configuring bandwidth allocation from an elastic network service provider in an elastic cloud computing network, allowing for on-demand access to variable bandwidth based on cost, capacity, and other parameters, eliminating the need for a dedicated link and enabling flexible scheduling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If bandwidth is provisioned to meet projected peak data demand, then data transfer capability during peak demand is sufficient, but bandwidth costs increase due to over-provisioning for significant periods
Solution Approach 1:
The patent implements dynamic bandwidth provisioning that automatically adjusts bandwidth allocation based on real-time monitoring of data transfer rates and predicted peak demand timing. The system transitions from static over-provisioning to dynamic adjustment, allocating maximum bandwidth only when peak demand is detected and reducing allocation during low-utilization periods, thereby maintaining reliability while minimizing costs.
Solution Approach 2:
The system changes the bandwidth allocation parameter dynamically based on monitored data transfer rates and predicted peak demand. By continuously adjusting the bandwidth parameter from a fixed high value to a variable value that matches actual demand, the system resolves the contradiction between maintaining sufficient transfer capability and reducing over-provisioning costs.
2Loss of energy
If bandwidth is reduced to lower costs, then bandwidth costs decrease during non-peak periods, but expensive overcharges occur when peak demand exceeds provisioned bandwidth
Solution Approach 1:
The system performs preliminary monitoring of data transfer rates to predict when peak demand will occur. By detecting trends in transfer rates before peak demand hits, the system proactively increases bandwidth allocation in advance, ensuring sufficient capacity is available when needed while avoiding premature or excessive provisioning that would increase costs.
Solution Approach 2:
The patent implements a feedback mechanism that continuously monitors actual data transfer rates and compares them against provisioned bandwidth. This feedback loop enables the system to detect when peak demand is approaching and adjust bandwidth allocation accordingly, preventing overcharges while maintaining reliability. The system learns from historical patterns to optimize future bandwidth decisions.
3Reliability
If dedicated bandwidth links are provisioned, then data transfer reliability is ensured, but device complexity and infrastructure costs increase
Solution Approach 1:
The patent makes the network bandwidth resource universal by allowing dynamic sharing among multiple data transfer tasks and applications. Instead of dedicating fixed bandwidth links to specific functions, the system creates a multi-functional bandwidth pool that can be allocated to different data transfer needs based on current demand, reducing infrastructure complexity while maintaining reliability through on-demand allocation.
Data Source
AI summary
Event-based data transfer scheduling using elastic network optimization criteria is provided. Bandwidth optimization criteria corresponding to different types of data transfer event scenarios are maintained, and based on recognizing a data transfer event scenario, a bandwidth optimization criteria is selected based on a type of the data transfer event scenario. A schedule for transferring data from a source to a target across the elastic network is determined according to the selected bandwidth optimization criteria, and the elastic network is used in transferring the data to the target storage location, where the using includes dynamically configuring elastic network bandwidth allocation from an elastic network service provider and initiating transfer of the data to the target storage location according to the schedule.