# alouach-07/wind-turbine-scada-forecasting-uq-tinyml architecture

> Architecture diagram of the GitHub repository alouach-07/wind-turbine-scada-forecasting-uq-tinyml, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-21). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml
- Repository: https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml

## Overview

This is a wind-turbine SCADA research pipeline: turbine histories are audited and converted into leakage-aware chronological windows, forecasting models produce next-step power and uncertainty, and analyses assess model behavior. A separate deployment branch distills two hybrid teachers into compact INT8 students and provides embedded inference artifacts. The README documents the broad workflow; sampled source confirms the TinyML inference path and distillation stages. Notebook internals and some unsampled model implementations are not inspected, so those links rely on README statements.

Main entry points: [`models/teachers`](https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/tree/main/models/teachers) (Forecast models), [`models/tinyml/scripts/train_students.py`](https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/models/tinyml/scripts/train_students.py) (Student training), [`notebooks/01_eda_and_data_quality.ipynb`](https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/notebooks/01_eda_and_data_quality.ipynb) (Data audit), [`notebooks/02_forecasting_and_uq.ipynb`](https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/notebooks/02_forecasting_and_uq.ipynb) (Window preparation)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["SCADA preparation"]
  node_audit["Data audit"]
  node_windows["Window preparation"]
end

subgraph group_research["Forecasting and analysis"]
  node_teachers["Forecast models"]
  node_uq["Uncertainty evaluation"]
  node_results["Forecast results"]
  node_xai["Explainability"]
  node_xairesults["XAI results"]
end

subgraph group_deployment["TinyML distillation"]
  node_targetexport["Teacher targets"]
  node_studenttrain["Student training<br/>[train_students.py]"]
  node_gruartifact["GRU student artifacts"]
  node_xgbartifact["XGBoost student artifacts"]
end

subgraph group_firmware["Embedded inference"]
  node_gruinference["GRU TinyML inference"]
  node_xgbinference["XGBoost TinyML inference"]
end

node_dataset["Kelmarsh SCADA"]
node_operator(("Turbine operator"))

node_dataset -->|"audited in"| node_audit
node_audit -->|"precedes"| node_windows
node_windows -->|"feeds histories"| node_teachers
node_teachers -->|"predicts uncertainty"| node_uq
node_teachers -->|"benchmarked in"| node_results
node_teachers -->|"analyzed by"| node_xai
node_xai -->|"exports rankings"| node_xairesults
node_teachers -->|"provides teacher outputs"| node_targetexport
node_targetexport -->|"supplies targets"| node_studenttrain
node_studenttrain -->|"exports student"| node_gruartifact
node_studenttrain -->|"exports student"| node_xgbartifact
node_gruartifact -->|"loads model data"| node_gruinference
node_xgbartifact -->|"loads model data"| node_xgbinference
node_operator -.->|"supplies window"| node_gruinference
node_operator -.->|"supplies window"| node_xgbinference

click node_audit "https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/notebooks/01_eda_and_data_quality.ipynb"
click node_windows "https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/notebooks/02_forecasting_and_uq.ipynb"
click node_teachers "https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/tree/main/models/teachers"
click node_uq "https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/notebooks/02_forecasting_and_uq.ipynb"
click node_results "https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/tree/main/results/forecasting"
click node_xai "https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/notebooks/03_explainability.ipynb"
click node_xairesults "https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/tree/main/results/xai"
click node_targetexport "https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/models/tinyml/scripts/export_teacher_targets.py"
click node_studenttrain "https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/models/tinyml/scripts/train_students.py"
click node_gruartifact "https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/tree/main/models/tinyml/gru_fastkan_uq_tinyml"
click node_xgbartifact "https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/tree/main/models/tinyml/xgboost_fastkan_uq_tinyml"
click node_gruinference "https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/models/tinyml/gru_fastkan_uq_tinyml/tinyml_inference.cc"
click node_xgbinference "https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/models/tinyml/xgboost_fastkan_uq_tinyml/tinyml_inference.cc"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_audit,node_windows toneBlue
class node_teachers,node_uq,node_results,node_xai,node_xairesults toneAmber
class node_targetexport,node_studenttrain,node_gruartifact,node_xgbartifact toneMint
class node_gruinference,node_xgbinference toneRose
class node_dataset,node_operator toneIndigo
```

## Components

### SCADA preparation

- [Data audit](https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/notebooks/01_eda_and_data_quality.ipynb): `notebooks/01_eda_and_data_quality.ipynb`
- [Window preparation](https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/notebooks/02_forecasting_and_uq.ipynb): `notebooks/02_forecasting_and_uq.ipynb`

### Forecasting and analysis

- [Forecast models](https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/tree/main/models/teachers): `models/teachers`
- [Uncertainty evaluation](https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/notebooks/02_forecasting_and_uq.ipynb): `notebooks/02_forecasting_and_uq.ipynb`
- [Forecast results](https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/tree/main/results/forecasting): `results/forecasting`
- [Explainability](https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/notebooks/03_explainability.ipynb): `notebooks/03_explainability.ipynb`
- [XAI results](https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/tree/main/results/xai): `results/xai`

### TinyML distillation

- [Teacher targets](https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/models/tinyml/scripts/export_teacher_targets.py): `models/tinyml/scripts/export_teacher_targets.py`
- [Student training](https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/models/tinyml/scripts/train_students.py): `models/tinyml/scripts/train_students.py`
- [GRU student artifacts](https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/tree/main/models/tinyml/gru_fastkan_uq_tinyml): `models/tinyml/gru_fastkan_uq_tinyml`
- [XGBoost student artifacts](https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/tree/main/models/tinyml/xgboost_fastkan_uq_tinyml): `models/tinyml/xgboost_fastkan_uq_tinyml`

### Embedded inference

- [GRU TinyML inference](https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/models/tinyml/gru_fastkan_uq_tinyml/tinyml_inference.cc): `models/tinyml/gru_fastkan_uq_tinyml/tinyml_inference.cc`
- [XGBoost TinyML inference](https://github.com/alouach-07/wind-turbine-scada-forecasting-uq-tinyml/blob/main/models/tinyml/xgboost_fastkan_uq_tinyml/tinyml_inference.cc): `models/tinyml/xgboost_fastkan_uq_tinyml/tinyml_inference.cc`

### Other components

- **Kelmarsh SCADA**
- **Turbine operator**

## Connections

- Kelmarsh SCADA → Data audit: audited in (evidence: `README.md`)
- Data audit → Window preparation: precedes (evidence: `README.md`)
- Window preparation → Forecast models: feeds histories (evidence: `README.md`)
- Forecast models → Uncertainty evaluation: predicts uncertainty (evidence: `README.md`)
- Forecast models → Forecast results: benchmarked in (evidence: `README.md`)
- Forecast models → Explainability: analyzed by (evidence: `README.md`)
- Explainability → XAI results: exports rankings (evidence: `README.md`)
- Forecast models → Teacher targets: provides teacher outputs (evidence: `README.md`)
- Teacher targets → Student training: supplies targets (evidence: `models/tinyml/scripts/train_students.py`)
- Student training → GRU student artifacts: exports student (evidence: `models/tinyml/scripts/train_students.py`)
- Student training → XGBoost student artifacts: exports student (evidence: `models/tinyml/scripts/train_students.py`)
- GRU student artifacts → GRU TinyML inference: loads model data (evidence: `models/tinyml/gru_fastkan_uq_tinyml/tinyml_inference.cc`)
- XGBoost student artifacts → XGBoost TinyML inference: loads model data (evidence: `models/tinyml/xgboost_fastkan_uq_tinyml/tinyml_inference.cc`)
- Turbine operator → GRU TinyML inference: supplies window
- Turbine operator → XGBoost TinyML inference: supplies window
