AI Container Routing for Data Center Energy Mix Optimization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Energy optimization is hindered by intermittency, outages, and the fluctuation of energy availability, making it difficult to identify optimal data center computing systems and energy mixes for event processing requests, while also posing security risks due to sensitive information interception.

Innovation Solution

A computing platform trains an energy optimization model to identify optimal data centers and energy mixes using AI, packages requests into secure containers, encrypts them, and routes them to data centers for processing, ensuring efficient and secure energy usage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If event processing requests are routed to various different processing systems to reduce delay, then processing speed is improved, but it becomes difficult to identify optimal alternatives due to constant fluctuation of energy availability and request parameters

Engineering Contradiction:

Improveprocessing speedVSAvoidsystem complexity

Core Design Contradiction:

SpeedVSDevice complexity

Solution Approach 1:

The patent introduces an energy optimization model as an intermediary component that sits between the event processing system and the data center infrastructure. This model receives event parameters and energy availability data, then outputs optimal data center routing decisions. The intermediary handles the complexity of real-time optimization, allowing the event processing system to maintain high speed while the model manages the computational burden of identifying optimal alternatives under fluctuating conditions.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Loss of energy

If an energy optimization model is trained to identify optimal data centers and energy mixes, then energy cost is reduced, but computing resources such as memory and processing power are consumed

Engineering Contradiction:

Improveenergy costVSAvoidcomputing resource consumption

Core Design Contradiction:

Loss of energyVSUse of energy by moving object

Solution Approach 1:

The energy optimization model is trained in advance using historical event processing data, energy pricing information, and processing capacity data from multiple data centers. This preliminary training phase allows the model to learn optimal routing strategies and energy mix selections before actual event processing occurs. During runtime, the pre-trained model can quickly query and apply learned patterns without requiring intensive real-time computation, thus reducing ongoing computing resource consumption while maintaining energy cost optimization.

Inventive Principle:

Principle #10Preliminary action

3Loss of information

If event processing requests include sensitive information, then data value is increased, but security risk increases due to potential interception by bad actors

Engineering Contradiction:

Improvedata valueVSAvoidsecurity risk

Core Design Contradiction:

Loss of informationVSObject-affected harmful factors

Solution Approach 1:

The patent extracts sensitive information from the event processing requests and stores it separately in secure storage, away from the main processing pipeline. Only non-sensitive event parameters are transmitted through the optimization model and routing system. This extraction approach allows the system to process and optimize routing for valuable events without exposing the sensitive data to potential interception risks during transmission and processing.

Inventive Principle:

Principle #2Taking out (Extraction)

4Productivity

If multiple data center computing systems are used for event processing, then processing capacity is increased, but difficulty in identifying optimal alternatives increases due to fluctuating energy availability

Engineering Contradiction:

Improveprocessing capacityVSAvoidoptimization difficulty

Core Design Contradiction:

ProductivityVSDifficulty of detecting and measuring

Solution Approach 1:

The energy optimization model implements a feedback mechanism that continuously receives updates on energy availability, data center processing capacity, and event parameters. This real-time feedback allows the model to dynamically adjust routing decisions and re-evaluate optimal alternatives as conditions change. The feedback loop enables the system to manage the complexity of multiple fluctuating variables by continuously adapting to current system state, thus maintaining optimization effectiveness across multiple data centers with varying capacities and energy availability.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12518326B2Energy optimization platform using artificial intelligence for container routing

Publication Date: 2026.01.06 BANK OF AMERICA CORP

AI summary

Aspects of the disclosure relate to energy optimization. A computing platform may receive an event processing request, and may identify its parameters. The computing platform may package, based on the parameters, the event processing request into containers. The computing platform may input the parameters into an energy optimization model, which may identify: a data center computing system and an energy mix for processing the event processing request. The computing platform may encrypt the containers. The computing platform may send, to the data center computing system, the encrypted containers and commands directing the data center computing system to: decrypt the encrypted containers to identify the event processing request, and process the event processing request using the energy mix, which may cause the data center computing system to decrypt the encrypted containers and process the event processing request using the energy mix.