Building Load Shedding Control for Net Zero Energy Targets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing building management systems face challenges in optimally controlling facilities to achieve net zero energy consumption, particularly in scenarios where energy production and consumption are asynchronous, and there is a need for efficient load shedding strategies to balance energy demand and supply.
Innovation Solution
A method using machine learning models to determine load shedding priorities and implement load shedding by controlling building equipment based on generated scores, allowing for dynamic adjustment to achieve target energy consumption, including load shifting and shedding units as necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If traditional building management systems control equipment to meet energy targets, then energy consumption is reduced, but the system cannot adapt to asynchronous energy production and consumption patterns
Solution Approach 1:
The system dynamically adjusts equipment control strategies based on real-time energy production and consumption patterns. Machine learning models continuously learn from historical data and adapt to changing conditions, enabling the system to handle asynchronous energy patterns effectively while maintaining energy reduction goals.
Solution Approach 2:
The system implements closed-loop feedback control where energy consumption data and production data are continuously monitored and fed back to the control algorithm. This feedback mechanism allows the system to adjust load shedding decisions in real-time to match actual energy availability, resolving the contradiction between energy reduction and adaptability.
2Loss of energy
If load shedding is implemented to achieve net zero energy consumption, then energy balance is improved, but building operations and comfort may be disrupted
Solution Approach 1:
The system performs preliminary load shedding actions in advance of energy shortages by predicting future energy deficits using machine learning models. This proactive approach allows the system to gradually reduce loads rather than making abrupt changes, maintaining building operations and comfort while achieving net zero energy targets.
Solution Approach 2:
The system implements partial load shedding on non-critical equipment while maintaining full operation of critical building systems. By selectively applying load shedding only where necessary, the system achieves energy balance without significantly disrupting building operations or occupant comfort.
3Productivity
If machine learning models are used to determine load shedding priorities, then load shedding efficiency is improved, but system complexity increases
Solution Approach 1:
The system segments the building equipment into different priority groups based on their operational criticality and energy consumption patterns. Machine learning models evaluate each equipment segment independently, allowing for efficient load shedding decisions without requiring complex system-wide optimization, thus improving efficiency while managing complexity.
Data Source
AI summary
A controller for a plurality of units of equipment of a facility includes one or more processing circuits configured to determine whether load shedding will be needed to achieve a target energy consumption for the facility, in response to determining that the load shedding will be needed, generate a plurality of load shedding priority scores for the plurality of units of equipment indicating relative advantages of shedding different units of the plurality of units of the equipment, and control the plurality of units of equipment by shedding a first unit of the plurality of units based on the plurality of load shedding priority scores.