Energy Use Normalization via Temperature Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for normalizing energy usage across different environmental conditions are inaccurate and complex, making it difficult to compare energy usage between buildings in varying climates or with erratic weather patterns, and there is a need for improved forecasting to manage energy resources effectively in smart grids.
Innovation Solution
A computer-implemented method that generates temperature-normalized energy use intensity values by receiving energy use data and weather information, determining baseload values, and applying statistical models, such as neural networks, to account for building properties and occupancy, enabling accurate normalization and forecasting of energy use.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current normalization methods are used, then energy usage comparison is attempted, but accuracy deteriorates due to complex and inaccurate environmental adjustments
Solution Approach 1:
The energy usage is segmented into distinct components: baseload consumption and temperature-dependent consumption. This segmentation allows each component to be analyzed and normalized separately, improving accuracy while simplifying the overall approach by focusing on the dominant temperature relationship rather than attempting to model all environmental factors simultaneously.
Solution Approach 2:
The temperature-dependent component is extracted from the total energy usage using statistical models that identify and isolate the portion of energy consumption directly related to temperature variations. This extracted component can then be normalized independently, allowing for more accurate comparisons across different climate conditions.
2Measurement precision
If detailed statistical models are applied, then normalization accuracy improves, but computational complexity increases
Solution Approach 1:
The system creates simplified statistical representations (models) of the building's energy consumption patterns based on historical data. These statistical copies capture the essential temperature-energy relationship without requiring complex real-time simulations, enabling accurate normalization with reduced computational burden.
3Adaptability or versatility
If temperature normalization is applied, then energy comparison across climates improves, but dependency on temperature data increases
Solution Approach 1:
The statistical models are designed to be universally applicable across different buildings and climate zones. By establishing general temperature-normalization relationships that can be adapted to various structures, the system achieves broad climate comparability while relying on the same fundamental temperature data inputs, rather than requiring building-specific complex datasets.
Data Source
AI summary
Disclosed herein are methods and systems for normalizing an energy use intensity value to compensate for variations in energy usage due to environment. Also disclosed are methods and systems for forecasting energy use intensity values.