Site Management Workload Migration for Renewable Energy

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing techniques for managing workloads in data centers do not effectively consider power consumption when relocating applications, leading to excessive overhead and inefficient use of renewable energy.

Innovation Solution

A site management apparatus that forecasts renewable energy supply and demand, calculates adjustment amounts, and selects migration target workloads to optimize power usage by relocating workloads between sites based on energy management information and workload management data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If application relocation is performed to improve renewable energy utilization, then renewable energy utilization rate is improved, but power consumption overhead increases due to data copying and switching processing

Engineering Contradiction:

Improverenewable energy utilization rateVSAvoidpower consumption overhead

Core Design Contradiction:

ProductivityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary actions by forecasting renewable energy supply and demand before making relocation decisions. It calculates adjustment amounts and selects migration target workloads in advance based on predicted energy availability, thereby avoiding reactive relocation that would incur unnecessary data copying and switching overhead.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by continuously monitoring actual power consumption against forecasted values and adjusting workload migration decisions accordingly. The site management apparatus uses feedback from energy management information to optimize relocation timing and minimize power consumption overhead while maintaining renewable energy utilization goals.

Inventive Principle:

Principle #23Feedback

2Productivity

If workload migration is performed frequently to maximize renewable energy usage, then renewable energy utilization improves, but service level deterioration occurs due to repeated down time

Engineering Contradiction:

Improverenewable energy utilization rateVSAvoidservice level

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system applies partial action by selectively migrating only specific workloads (migration target workloads) rather than all workloads. It performs workload migration to the extent necessary to utilize renewable energy without excessive relocation that would cause service deterioration, balancing energy utilization with service level maintenance.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system performs preliminary selection of migration target workloads based on forecasted renewable energy supply and demand. By identifying which workloads should be migrated in advance and calculating adjustment amounts beforehand, the system minimizes unnecessary migration operations that would cause service level deterioration.

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If data copying is performed during application relocation, then application can be moved to different sites, but down time of several seconds to several minutes occurs causing power consumption overhead

Engineering Contradiction:

Improveapplication relocation capabilityVSAvoiddown time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by forecasting energy supply and demand and calculating adjustment amounts before initiating workload migration. This advance planning allows data copying and migration to be scheduled during periods of low impact, reducing down time and associated power consumption overhead.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The site management apparatus autonomously manages workload migration by automatically selecting migration target workloads and determining optimal migration timing based on energy forecasts. This self-service capability reduces manual intervention and optimizes the migration process to minimize down time and power consumption overhead.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS11823294B1Site management apparatus and management method

Publication Date: 2023.11.21 HITACHI VANTARA LTD

AI summary

There is provided a site management apparatus capable of achieving both the improvement of the utilization rate of renewable energy and the reduction of the overhead of power consumption. A processor calculates, based on a site energy management table, an adjustment amount for adjusting a demand amount consumed at a migration source site of a workload. The processor selects, based on the adjustment amount and workload management information, a migration target workload, which is a workload whose execution site is to be migrated to a migration destination site, from among workloads executed in the migration source site and generates migration plan information indicating the selected migration target workload.