Workload Distribution Model Aggregation Across Data Centers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems lack effective methods for monitoring and managing computing workload distribution across multiple data centers, leading to inefficient and costly resource utilization in mainframe computer environments.
Innovation Solution
A system that collects performance metrics from individual data centers, builds models of resource use for each central processor complex, and combines these models into a single multiplex model to optimize workload distribution across multiple data centers, allowing for user-selectable reporting versions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If computing workload is distributed across multiple data centers, then resource utilization efficiency is improved, but monitoring and management complexity increases
Solution Approach 1:
The patent segments the monitoring and management system into distributed agents deployed at each data center location. Each agent independently collects performance metrics and generates local models, which are then aggregated by a central service. This segmentation reduces the complexity at any single point while maintaining overall system effectiveness.
Solution Approach 2:
The patent introduces an intermediary workload distribution service that acts as a mediator between distributed data centers and end users. This service consolidates multiple data center interfaces into a single point of management, handling workload routing, model aggregation, and coordination, thereby reducing management complexity.
2Measurement precision
If performance metrics are collected from all data centers, then workload distribution accuracy is improved, but data collection and processing time increases
Solution Approach 1:
The patent implements preliminary action by having distributed agents continuously collect and pre-process performance metrics locally before central aggregation is needed. Each agent maintains up-to-date local models and can immediately respond to workload distribution decisions without waiting for centralized data collection, reducing processing time while maintaining accuracy.
Solution Approach 2:
The patent applies partial action by allowing the system to function effectively with locally-collected data at each data center. The central service aggregates these partial models rather than requiring complete centralized data collection, achieving sufficient accuracy without the time cost of collecting and processing all possible metrics centrally.
3Manufacturing precision
If individual models are built for each data center, then resource allocation precision is improved, but system complexity increases
Solution Approach 1:
The patent merges individual data center models into a unified workload distribution model. The central service combines local models from multiple data centers, integrating their resource allocation precision while presenting a single simplified interface for workload management. This merging maintains high allocation precision without proportionally increasing system complexity.
Solution Approach 2:
The patent creates a universal workload distribution service that handles multiple functions: collecting metrics from various data centers, building local models, aggregating these models, and making distribution decisions. This multi-functional approach consolidates complexity into a single system component rather than requiring separate specialized systems for each function.
Data Source
AI summary
A system includes, for each individual data center of a multiplex data center, a collector component, a local data repository, and a model building component. The collector component collects performance metrics of a computing workload running in the each individual data center of the multiplex data center and stores the collected performance metrics in the local data repository. The model building component builds a respective individual model of data center resource use for each individual CPC in the individual data center using the stored performance metrics. The system further includes a model merging component configured to receive and combine the individual CPC models created by the model building components for the individual data centers into a single multiplex data center model applicable to the computing workload across the multiplex data center.