Regression Model Anomaly Detection for PV Systems

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for monitoring electrical generation systems, such as PV solar facilities, face challenges in accurately identifying operational anomalies due to the manual selection of datasets and the inclusion of data from irregular conditions, which can distort the relationship between environmental factors and power output.

Innovation Solution

The development and maintenance of regression models that filter out data points outside a certain standard deviation range, excluding outliers and data from irregular conditions like varying cloud cover, to create a tightly filtered dataset that accurately predicts electrical power output based on environmental and operational factors.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual selection of datasets is used to create regression models, then the models can be created with expert knowledge, but the process is time consuming and requires highly skilled experts

Engineering Contradiction:

Improvemodel accuracyVSAvoidtime to create model

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs automatic dataset selection and regression model creation without requiring manual expert intervention. The computer system autonomously evaluates collected data, identifies suitable datasets based on predefined criteria, and generates regression models automatically, eliminating the need for time-consuming manual selection by skilled experts

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The manual mechanical process of expert-driven dataset selection and model creation is replaced with an automated computational system. The computer system uses algorithms to perform data evaluation, selection, and model generation, substituting human expert mechanics with automated computational mechanics

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Quantity of substance

If all collected data is used to create regression models, then more data is available for modeling, but data from irregular conditions like varying cloud cover distorts the relationship between environmental factors and power output

Engineering Contradiction:

Improvedata volumeVSAvoidmodel accuracy

Core Design Contradiction:

Quantity of substanceVSMeasurement precision

Solution Approach 1:

The system extracts and removes data points that do not represent normal operating conditions from the collected dataset. By identifying and excluding data from irregular conditions such as varying cloud cover, the system creates a refined dataset that contains only relevant information for accurate regression modeling of the relationship between environmental factors and power output

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system changes the state of the dataset by applying filtering criteria based on operational parameters. Data points are evaluated against defined parameters for normal operation, and those that do not meet the criteria are excluded, transforming the raw data into a refined dataset suitable for accurate modeling

Inventive Principle:

Principle #35Parameter changes

3Reliability

If manually selected good datasets are used, then the datasets represent proper operation without anomalies, but the manual selection process is time consuming

Engineering Contradiction:

Improvedata qualityVSAvoidtime to select dataset

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The computer system autonomously performs dataset selection by evaluating collected data against predefined criteria for normal operation. The system automatically identifies and selects datasets that represent proper operation without anomalies, eliminating the time-consuming manual selection process while maintaining high data quality standards

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system uses feedback mechanisms to evaluate data quality and operational normality. By continuously assessing data points against established criteria and adjusting selections based on this feedback, the system automatically identifies reliable datasets without manual intervention, ensuring high data quality while reducing time consumption

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11086278B2Adaptive system monitoring using incremental regression model development

Publication Date: 2021.08.10 INVENTUS HOLDINGS LLC

AI summary

Systems and methods for monitoring an operational system. A data set with output power values and associated environmental data values for an electrical generation system are accumulated. Statistical relationships are determined for output power values and environmental data values. Outlying data is determined based on the statistical relationships and are removed from the data set to create selected data. A regression model is developed from the selected data to map predicted output power values to values of environmental data. Data with present output power values and present associated environmental data for the electrical generation system are later received. Predicted output power values are predicted by the regression model for the present associated environmental data. An output power discrepancy is identified by comparing the predicted output power to the present output power. A notification of an anomaly is provided based on identification of the output power discrepancy.