Data Center Location Selection Using Energy Forecasting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computing workload management systems fail to consider real-time and future energy factors, leading to increased IT power costs and indirect expenses such as equipment cooling, resulting in unnecessary disruptions and added expenses for businesses.
Innovation Solution
A system and method for selecting an optimal location for running computational workloads based on multivariate and predictive analysis of total direct and indirect energy costs, using a data collector, forecasting module, and rules engine to calculate power costs, temperature differentials, and other factors, allowing for flexible addition of energy attributes and criteria weighting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If computational workloads are processed within a data center using traditional methods, then data processing can be performed, but IT power costs and indirect power related costs (such as equipment cooling) increase significantly
Solution Approach 1:
The system dynamically selects optimal data center locations based on real-time and predictive energy factors. The location selection is not fixed but adapts to changing energy conditions, allowing the workload to be routed to data centers with favorable energy characteristics at the time of execution, thereby reducing overall power costs while maintaining processing capability
Solution Approach 2:
The invention changes the parameters considered for data center selection from traditional factors (availability, performance) to include energy-related parameters such as real-time power costs, temperature differentials, and predictive energy factors. This parameter expansion enables cost optimization by selecting data centers with more favorable energy parameters
2Productivity
If traditional data center location selection methods are used, then workloads can be processed, but indirect power related costs such as equipment cooling cause significant burden on business IT budgets
Solution Approach 1:
The system performs preliminary analysis of energy factors before workload execution. By predicting future energy conditions and pre-selecting optimal data center locations based on projected energy costs and temperature differentials, the system avoids implementing workloads in locations that would result in high cooling costs, thereby reducing indirect power-related energy losses
3Device complexity
If location selection does not consider real-time and future energy factors, then simple selection methods can be used, but unnecessary disruptions and added expense occur
Solution Approach 1:
The system incorporates real-time feedback on energy conditions and predictive forecasts into the location selection process. By continuously monitoring actual energy consumption and comparing it with predictions, the system can adjust location selections to avoid disruptions caused by unexpected energy conditions, thereby improving reliability without excessive complexity
Data Source
AI summary
The selection of an optimal data center location for running a computational workload is based on multiple energy criteria. The location is chosen based on multivariate and predictive analysis of total direct and indirect energy costs, and other user-defined factors. Among the direct and indirect costs are power costs and cooling costs as well as structural and other details of a given data center. Among the other factors to be considered that can have an impact on present and future costs are weather patterns, data and forecasts, availability of energy providers, and energy attributes. A forecaster factors these direct and indirect costs along with extrinsic information such as historical trends and predictive sources into a forecast which is then input to a decision engine along with user defined criteria and with anticipated compute tasks and requirements to select a final location or locations for handling the workload.