Building Energy Scheduling Using Predictive Demand Response
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current energy minimization systems in buildings operate only during peak periods using fixed demand response schedules, lack optimization based on different demand response methods, require manual analysis by energy analysts, and do not predict energy savings before deployment of energy-saving methods, leading to inefficient energy management and increased costs.
Innovation Solution
A system that predicts energy savings by analyzing demand response schedules, user preferences, and environmental factors, using various demand response algorithms and an energy optimized schedule generator to create a dynamic energy schedule, which can be adjusted to minimize energy consumption and maintain occupant comfort, including features like zone temperature set point adjustment, pre-cooling, and load-based chiller scheduling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If fixed demand response schedules are used during peak periods, then energy consumption is reduced, but energy optimization is limited and cannot adapt to different demand response methods or conditions
Solution Approach 1:
The system transitions from fixed demand response schedules to dynamic optimized energy schedules that adapt in real-time based on predicted environmental conditions, user preferences, and multiple demand response algorithms. The schedule is continuously adjusted to optimize energy consumption under varying conditions rather than following predetermined fixed patterns.
Solution Approach 2:
The system changes multiple parameters simultaneously including set point temperatures, pre-cooling durations, chiller scheduling, and zone configurations to generate optimized energy schedules. This multi-parameter optimization enables adaptation to different demand response methods and conditions while maximizing energy reduction.
2Loss of information
If manual analysis by energy analysts is required, then energy data can be interpreted, but the process is time-consuming and requires human intervention
Solution Approach 1:
The system performs automated energy data interpretation and optimization without requiring manual analysis by energy analysts. The demand response algorithms automatically process energy data, predict environmental conditions, generate optimized schedules, and implement energy-saving measures, enabling the system to serve itself rather than relying on human intervention.
Solution Approach 2:
The system replaces the mechanical process of manual data analysis with automated computational algorithms. The demand response algorithms and optimization engine substitute human analysts, using computer-based processing to interpret energy data, predict conditions, and generate optimized schedules automatically.
3Measurement precision
If energy savings are predicted only after deployment, then actual savings can be measured, but proactive optimization and visualization before deployment is not possible
Solution Approach 1:
The system performs preliminary prediction of energy savings and generates optimized energy schedules before deployment. By predicting environmental conditions and running demand response algorithms in advance, the system can visualize expected energy savings and allow user adjustment before implementation, enabling proactive rather than reactive optimization.
Solution Approach 2:
The system provides feedback on predicted energy savings and schedule effectiveness both before and after deployment. The visualization of predicted savings gives users feedback to adjust parameters, while post-deployment measurement provides validation feedback, creating a continuous improvement loop.
4Loss of energy
If multiple demand response algorithms and dynamic scheduling are implemented, then energy optimization is improved, but system complexity increases
Solution Approach 1:
The system uses multiple demand response algorithms that can handle different scenarios and conditions, making the system universally applicable to various building types, climates, and operational requirements. This multi-functionality allows a single system to address diverse optimization needs without requiring separate specialized systems for each scenario.
Solution Approach 2:
The optimized energy schedule acts as an intermediary that translates complex algorithmic outputs into actionable set point adjustments and operational changes. This intermediary layer simplifies the interface between the complex demand response algorithms and the actual building equipment control, making the system more manageable despite its computational complexity.
Data Source
AI summary
A system receives an energy demand response schedule, one or more user preferences, and one or more predicted environmental variables into a computer processor. The system generates an optimized energy schedule as a function of the demand response schedule, the user preferences, and the predicted environmental variables. The optimized energy schedule includes one or more of a set point temperature variation in one or more zones, an air handling unit set point temperature variation, a chilled water set point temperature variation, a carbon dioxide level set point variation, a pre-cooling time shift, a pre-cooling duration variation, and a load based optimized chiller schedule. The system transmits the optimized energy schedule to a building management server.