Facility Load Curtailment Using AI Peak Demand Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Commercial facilities face high utility demand charges due to peak electricity demand, which can account for 30-70 percent of total utility charges, despite similar overall electricity consumption.
Innovation Solution
The system uses AI/ML models to predict power usage peaks based on live and historical data, identifies contributing loads, and controls these loads to curtail power usage during predicted peaks, thereby reducing demand charges.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If facilities operate equipment to meet demand during peak periods, then service reliability is improved, but utility demand charges increase
Solution Approach 1:
The system performs preliminary action by predicting peak demand periods in advance using AI/ML models and pre-scheduling equipment operations during off-peak hours. This allows facilities to maintain service reliability while avoiding peak demand charges by completing necessary operations before the predicted peak occurs.
Solution Approach 2:
The system implements dynamic load management by continuously monitoring real-time power usage data and dynamically adjusting equipment schedules based on predicted peak demand periods. The AI/ML model adapts to changing patterns and optimizes equipment operation timing to balance reliability needs with demand charge reduction.
2Use of energy by stationary object
If facilities curtail power usage during peak periods, then utility demand charges are reduced, but service quality may deteriorate
Solution Approach 1:
The system performs preliminary action by pre-scheduling essential equipment operations during off-peak hours before the predicted peak demand occurs. This ensures that necessary services are completed in advance, maintaining service quality while avoiding peak period operation that would incur high demand charges.
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring actual power usage against predicted patterns and adjusting future predictions and schedules accordingly. This closed-loop control ensures that service quality requirements are met while optimizing demand charge reduction strategies.
3Use of energy by stationary object
If facilities use AI/ML models for predictive load management, then demand charge reduction is improved, but system complexity increases
Solution Approach 1:
The system implements self-service by using AI/ML models that automatically learn from historical and real-time power usage data without requiring extensive manual configuration or intervention. The models autonomously predict peak demand periods and generate optimized equipment schedules, reducing the operational complexity despite the advanced analytics involved.
Solution Approach 2:
The AI/ML prediction model serves as an intermediary between raw power usage data and load management decisions. This intermediary layer processes complex data patterns and translates them into actionable scheduling recommendations, simplifying the overall system architecture while enabling sophisticated demand charge optimization.
Data Source
AI summary
Live and historical power usage data of one or more loads of a facility may be provided to an AI/ML (Artificial Intelligence/Machine Learning) model. The AI/ML model predicts one or more predicted power usage peaks that are predicted to occur during a future time window based at least in part on the live and historical power usage data of the one or more loads of the facility. One or more loads of the facility are identified that are predicted to contribute to each of the one or more predicted power usage peaks. One or more of the loads of the facility that are predicted to contribute to a selected one of the one or more predicted power usage peaks are controlled to curtail power usage during the selected one of the one or more predicted power usage peaks.