Building Energy Management Using AI for Grid-Responsive Load Shifting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing building energy management systems do not effectively manage energy demand to match supply, leading to excess energy production during low demand periods and insufficient energy during high demand periods, resulting in costly stand-by generation and inefficient energy usage.
Innovation Solution
A building energy management system that uses an artificial neural network to predict energy needs based on consumption patterns, weather, and energy prices, and adjusts energy storage and consumption to match grid supply conditions, allowing for responsive energy drawdown during excess supply and reduced draw during high demand, utilizing blockchain for financial incentives and capacity management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If energy management systems passively monitor and provide information to building managers, then building energy performance can be understood and controlled, but the system cannot automatically respond to grid supply conditions or smooth demand variations
Solution Approach 1:
The energy management system automatically responds to grid supply conditions and demand signals without requiring manual intervention. The system self-adjusts energy consumption patterns based on real-time pricing signals and supply conditions, enabling automatic load shifting and demand response actions
Solution Approach 2:
The system continuously receives feedback from the grid regarding supply conditions, pricing signals, and demand responses. This feedback loop enables the system to dynamically adjust energy consumption patterns, automatically responding to changing grid conditions and optimizing energy usage based on real-time information
2Reliability
If stand-by power generation systems are brought on stream to meet extra demand, then energy supply reliability is maintained, but generation costs increase significantly
Solution Approach 1:
The system performs preliminary actions by pre-cooling or pre-heating buildings during periods of low demand and low energy prices. Energy storage systems are charged in advance during off-peak hours, enabling the building to maintain comfortable temperatures without relying on expensive stand-by generation during peak demand periods
Solution Approach 2:
The system changes operational parameters of energy-consuming assets based on grid conditions and pricing signals. By adjusting temperature setpoints, scheduling energy-intensive operations during off-peak hours, and modifying load patterns, the system reduces dependence on stand-by generation while maintaining supply reliability
3Quantity of substance
If energy generation systems produce excess energy during low demand, then supply capacity is available, but the excess energy must be managed through costly tariffs or waste
Solution Approach 1:
The system continuously utilizes excess energy supply by maintaining energy storage systems charged during periods of excess supply. Rather than allowing excess energy to go to waste or incur costly tariffs, the system continuously draws from storage during peak demand periods, transforming intermittent excess supply into continuous useful action
Solution Approach 2:
The system recovers value from excess energy supply by storing it during low-demand periods when supply exceeds demand. This recovered energy is then utilized during peak demand periods, effectively discarding the problem of excess supply and transforming it into a valuable energy resource for later use
4Loss of energy
If building energy management systems use artificial intelligence to optimize settings, then energy efficiency improves, but the system cannot address issues on the energy supply side or grid demand regulation
Solution Approach 1:
The energy management system performs multiple functions: it optimizes building energy efficiency through AI-driven control of HVAC and lighting systems, simultaneously responds to grid supply conditions, participates in demand response programs, and manages energy storage. This multi-functional capability allows the system to address both building-level efficiency and grid-level supply side issues
Data Source
AI summary
A building comprises a network of energy storage and energy consuming assets, which is connected to an alternating current electric supply grid having a normal frequency through an energy management system linked to a server. The energy management system measures over a period of time the energy consumption against time of the energy consuming assets and stores the measurements taken and measures over a period of time the energy stored against time in the energy storing assets and stores the measurements taken. The measurements of energy consumption and energy stored are used to derive the base net energy need in particular time periods. The net energy need in individual time periods is exported to one or more third parties.