Building Load Forecasting With Deterministic-Stochastic Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building management systems face challenges in accurately forecasting time series values such as load and energy consumption over short to medium horizons, which is crucial for optimizing energy usage and costs, due to the complexity of predicting varying loads and weather impacts.
Innovation Solution
A system that generates predictive models using deterministic and stochastic models, trained with historical data, to forecast time series values, adjusting forecasts based on actual values and residuals, and optimizing control actions for building equipment to manage energy usage effectively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If a building management system uses optimization techniques to minimize energy consumption and cost, then energy efficiency is improved, but accurate forecasting of future loads and performance becomes more difficult and challenging
Solution Approach 1:
The patent segments the forecasting problem into multiple time horizons (short-term, medium-term, long-term forecasts) and uses different modeling approaches for each horizon. This segmentation allows the system to address the complexity of forecasting by breaking it into manageable components, thereby improving forecasting accuracy while maintaining energy optimization capabilities.
Solution Approach 2:
The patent implements dynamic forecasting models that adapt to changing conditions and incorporate historical data patterns. The system dynamically adjusts forecasts based on seasonal variations, weather conditions, and historical performance, enabling accurate predictions across different time horizons while supporting continuous energy optimization.
2Duration of action of moving object
If the forecasting horizon is extended to optimize energy usage over longer periods, then energy management capability is improved, but prediction accuracy deteriorates due to increased uncertainty
Solution Approach 1:
The patent divides the forecasting horizon into distinct segments (short-term, medium-term, long-term) and applies appropriate modeling techniques to each segment. This allows the system to maintain higher accuracy for immediate forecasts while providing strategic guidance for longer-term planning, effectively resolving the trade-off between horizon duration and prediction precision.
Solution Approach 2:
The patent changes the parameters and complexity of forecasting models based on the time horizon being predicted. Short-term forecasts use more detailed, high-frequency data with complex models, while long-term forecasts use aggregated data with simplified models, thereby maintaining acceptable accuracy across different forecasting durations.
3Adaptability or versatility
If a building management system implements comprehensive monitoring and control of building functions, then system capability is improved, but device complexity increases
Solution Approach 1:
The patent implements a universal forecasting platform that serves multiple building functions and time horizons through a single integrated system. This multi-functional approach provides comprehensive monitoring and control capabilities while avoiding the complexity of separate specialized systems, as the core forecasting engine handles diverse forecasting needs across different building operations.
Data Source
AI summary
A building management system (BMS) includes sensors that measure time series values of building variables and a deterministic model generator that uses historical values for the time series of building variables to train a deterministic model that predicts deterministic values for the time series. The BMS includes a stochastic model generator that uses differences between actual values for the time series and the predicted deterministic values to train a stochastic model that predicts a stochastic value for the time series. The BMS includes a forecast adjuster that adjusts the predicted deterministic values using the predicted stochastic value to generate an adjusted forecast for the time series. The BMS includes a demand response optimizer that uses the adjusted forecast to generate an optimal set of control actions for building equipment of the BMS. The building equipment operate to affect the building variables.