Energy Load Modeling Using Partition Variables for Multi-Mode Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to effectively model physical systems with distinct operating modes, such as energy load management systems, as they often require separate models for each regime of operation, leading to inefficiencies in energy consumption monitoring and management.
Innovation Solution
A computer-implemented method and system that uses a load monitoring server to define influencing drivers and partition variables, creating models for each discrete value of the partition variables to accurately predict energy load behavior, allowing for efficient monitoring and management of energy consumption across different operating modes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If separate models are created for each operating regime, then modeling accuracy for each regime is improved, but system complexity and number of models required increases
Solution Approach 1:
The patent segments the operating space by introducing discrete partition variables that divide continuous operating conditions into distinct regimes. Each regime has its own optimized model, allowing high accuracy within each segment while managing overall system complexity through structured organization of multiple specialized models rather than one complex universal model.
Solution Approach 2:
The system dynamically selects which partition variable discretization to apply based on current operating conditions. The partition variables and their discrete values are not fixed but can be adjusted to match the actual operating regimes encountered, allowing the modeling approach to adapt to changing system behavior patterns.
2Device complexity
If a single model is used for all operating regimes, then system simplicity is maintained, but modeling accuracy deteriorates across different modes
Solution Approach 1:
Instead of applying one uniform model structure across all operating conditions, the patent applies different model configurations locally to different operating regimes. Each partition variable discretization creates local models optimized for specific conditions, ensuring high prediction accuracy for each local regime while maintaining overall system manageability.
3Adaptability or versatility
If partition variables are discretized into multiple values, then operating conditions are better represented, but data requirements and processing complexity increase
Solution Approach 1:
The system applies partition variable discretization selectively rather than to all variables and conditions. By choosing which variables to discretize and how many discrete values to create, the system achieves sufficient operating condition coverage without unnecessarily increasing data processing complexity. The discretization level is optimized to provide adequate representation without excessive detail.
Data Source
AI summary
A system, method, and computer program product for predicting operation for physical systems with distinct operating modes uses observable qualities of the system to predict other qualities of the system. Independent variables including temperature or production volume are observed to determine the degree to which a dependent modeled variable, including energy load, is influenced. Partition variables representing operating conditions of the dependent variables are defined as discrete values. Reference datasets with coincident values of the dependent variable, independent variable, and partition variables are received, and models are created for each discrete value of the partition variables in the reference dataset. Each model is populated with the values of the dependent variable and the independent variable. The dependent variable is modeled as a function of the independent variable. Model accuracy is evaluated by processing new input data to generate output data that includes values of the coincident dependent variable, the independent variable, and the partition variable from the input dataset.