Dynamic Load Curtailment Using Historical Peak Demand Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing energy management systems for load curtailment often require extensive tuning and retuning due to seasonal changes, leading to either inadequate or excessive energy reduction, causing occupant disruption and inefficiency.
Innovation Solution
A dynamic load curtailment algorithm that learns optimum energy consumption conditions for a building by employing separate control schemes for HVAC and non-HVAC loads, using historical peak demand measurements to predict and strategically curtail loads within user-configured parameters, ensuring minimal peak demand while maintaining occupant comfort.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If schedule or threshold-based curtailment systems are used, then energy consumption is reduced, but extensive tuning and retuning are required to avoid occupant disruption
Solution Approach 1:
The system performs self-tuning by automatically learning building-specific patterns and parameters through continuous monitoring of historical data. The algorithm adapts to seasonal changes and occupancy patterns without requiring manual intervention, eliminating the need for extensive tuning and retuning while maintaining optimal energy curtailment.
Solution Approach 2:
The system continuously monitors energy consumption, occupancy patterns, and environmental conditions, using this feedback to dynamically adjust curtailment strategies. This closed-loop approach allows the system to learn from past performance and automatically optimize parameters, reducing the need for manual tuning while maintaining energy efficiency.
2Productivity
If manual tuning is performed to optimize curtailment, then energy efficiency improves, but occupant disruption occurs when tuning is inadequate or excessive
Solution Approach 1:
The system dynamically adjusts curtailment parameters based on real-time conditions and learned patterns rather than using fixed schedules or thresholds. This dynamic approach allows the system to optimize energy efficiency while automatically adapting to changing occupancy and environmental conditions, preventing occupant disruption.
Solution Approach 2:
The algorithm continuously learns and adapts to building-specific patterns, automatically tuning curtailment strategies to achieve optimal energy efficiency without manual intervention. This self-tuning capability ensures that curtailment remains efficient while avoiding occupant disruption, as the system learns the building's unique characteristics and occupancy patterns over time.
3Loss of energy
If fixed curtailment schedules are implemented, then energy consumption is reduced, but the system cannot adapt to seasonal changes without retuning
Solution Approach 1:
The system transitions from fixed schedules to dynamic, adaptive curtailment strategies that automatically adjust to seasonal changes and varying conditions. The algorithm continuously learns from historical data and environmental inputs, enabling the system to maintain energy efficiency across different seasons and conditions without requiring manual retuning.
Solution Approach 2:
The system performs self-adaptation by continuously monitoring environmental conditions, occupancy patterns, and energy consumption data. This self-learning capability allows the system to automatically adjust to seasonal changes and building-specific patterns, maintaining optimal energy efficiency without requiring external intervention or retuning.
Data Source
AI summary
A system and method are disclosed for dynamically learning the optimum energy consumption operating condition for a building and monitor/control energy consuming equipment to keep the peak demand interval at a minimum. The dynamic demand limiting algorithm utilized employs two separate control schemes, one for HVAC loads and one for non-HVAC loads. Separate operating parameters can be applied to the two types of loads and multiple non-HVAC (control zones) loads can be configured. The algorithm uses historical peak demand measurements in its real-time limiting strategy. The algorithm continuously attempts to reduce peak demand within the user configured parameters. When a new peak is inevitable, the algorithm strategically removes and/or introduces loads in a fashion that limits the new peak magnitude and places the operating conditions within the user configured parameters. In an embodiment, the algorithm that examines the previous seven days of metering information to identify a peak demand interval. The system then uses real-time load information to predict the demand peak of the upcoming interval, and strategically curtails assigned loads in order to limit the demand peak so as not to set a new peak.