Cloud-Edge Integrated Energy Optimizer to Reduce Control Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing building energy management systems face data transfer latency and IT security concerns, particularly in large buildings, which hinder real-time energy optimization and setpoint control.
Innovation Solution
The system splits optimization and control between an edge device for real-time data processing and a cloud for analytics, using model predictive control and big data analytics to optimize energy usage while minimizing latency and enhancing security.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If data is transferred from building management system to cloud for optimization, then energy optimization can be performed, but data transfer latency increases and real-time control is hindered
Solution Approach 1:
The system segments the energy optimization function into two parts: real-time control operations remain at the edge device (building management system), while analytics and model improvement are performed on the cloud. This segmentation allows real-time control to proceed without cloud communication delays, while still benefiting from cloud-based optimization analytics.
Solution Approach 2:
The patent introduces an intermediary approach where the edge device maintains local optimization capabilities using stored models, acting as a mediator between immediate control needs and cloud-based analytics. This intermediary local model enables real-time decision-making without requiring constant cloud communication, thus reducing latency while still achieving energy optimization.
2Loss of energy
If setpoint changes are controlled from cloud, then centralized optimization is achieved, but IT security concerns increase and control latency increases
Solution Approach 1:
The system applies local quality by enabling the edge device to perform optimization operations locally using stored analytics models, rather than requiring all control decisions to originate from the cloud. This local optimization capability reduces security exposure while maintaining energy optimization benefits, as critical control functions remain within the local network boundary.
3Loss of information
If all optimization processing is done on cloud, then centralized analytics can be performed, but data transfer requirements increase and control responsiveness decreases
Solution Approach 1:
The system segments processing tasks by keeping lightweight local models at the edge device for rapid response, while sending aggregated data to the cloud for comprehensive analytics and model retraining. This segmentation enables both centralized analytics capability and fast local control responsiveness to coexist.
Solution Approach 2:
The cloud performs preliminary actions by training and updating analytics models offline, then pushing these pre-trained models to edge devices. This preliminary model preparation allows the edge device to execute optimization decisions instantly without requiring real-time cloud processing, thus achieving both centralized analytics and fast control response.
Data Source
AI summary
An integrated energy optimizer having an edge side and a cloud side. The edge side may incorporate an energy optimizer, a building management system connected to the energy optimizer, a controller connected to the building management system, and equipment connected to the controller. The cloud side may have a cloud connected to the energy optimizer and to the building management system, and a user interface connected to the cloud. Data from the field sensor may go to the optimizer and the building management system. The data may be processed at the optimizer and the building management system for proper settings at the building management system.