Machine-Learning Energy Performance Evaluation Under Variable Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing evaluation methods for energy saving effects in equipment operation are unreliable due to failure to accurately account for variations in operation environments and performance metrics across different periods, leading to inconsistent energy saving effect calculations.
Innovation Solution
An evaluation apparatus and method that acquires environmental and performance data, uses machine-learning models to estimate operation performance based on historical data, and calculates indicators to relatively evaluate actual performance against estimated performance, allowing for accurate energy saving effect quantification by aligning performance evaluations under consistent conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional energy saving effect calculation methods are used, then calculation simplicity is maintained, but evaluation reliability deteriorates due to failure to account for environmental variations
Solution Approach 1:
The system performs preliminary machine learning training during a learning target period to create prediction models before evaluating energy saving effects. Environmental data and performance data are collected and processed in advance to establish the relationship between operating conditions and equipment performance, enabling reliable evaluations without complex real-time adjustments
Solution Approach 2:
A machine learning model serves as an intermediary between environmental data and performance evaluation. The model learns the complex relationships between multiple environmental factors and equipment performance, then uses this learned knowledge to predict expected performance under different conditions, eliminating the need for direct complex calculations while maintaining high reliability
2Measurement precision
If environmental variations are not considered, then evaluation process simplicity is maintained, but measurement precision deteriorates
Solution Approach 1:
The evaluation process is segmented into distinct phases: a learning target period for model training and an evaluation target period for energy saving assessment. Environmental data is segmented into multiple dimensions (temperature, humidity, load conditions, etc.), and each is processed separately to understand its specific impact on performance, improving measurement precision without overwhelming complexity
Solution Approach 2:
The system changes parameters by using different environmental conditions as input variables to the machine learning model. By varying environmental parameters (temperature, humidity, operational load) and observing their impact on predicted performance, the system precisely measures energy saving effects while accounting for environmental variations through the learned relationships
3Measurement precision
If machine learning models are used to estimate operation performance, then evaluation accuracy is improved, but computational complexity increases
Solution Approach 1:
The machine learning model is trained in advance during a learning target period using historical environmental data and performance data. This preliminary training phase allows the model to learn complex relationships offline, so that during the evaluation phase, only simple prediction calculations are needed, achieving high accuracy without continuous computational complexity
Solution Approach 2:
The system uses a learning target period that may be longer than strictly necessary, collecting excessive data to thoroughly train the model. This ensures the model achieves high accuracy and robustness, and the resulting model can then be used efficiently for evaluation with minimal computational requirements
Data Source
AI summary
Provided is an evaluation apparatus comprising: an environmental data acquisition unit configured to acquire environmental data indicating an operation environment of equipment; a performance data acquisition unit configured to acquire performance data indicating an operation performance of the equipment; an estimation unit configured to estimate an operation performance on an operation basis in a learning target period under an operation environment in an evaluation target period, based on the environmental data and the performance data in the learning target period; an evaluation unit configured to calculate an indicator that relatively evaluates an actually measured value of an operation performance in the evaluation target period with respect to an estimated value of the estimated operation performance; and an output unit configured to output the indicator.