Experimental Telemetry Dataset and Codebase for Closed-Loop-TinyOL v2

Experimental Telemetry Dataset & Codebase: TinyOL for Edge Anomaly Detection and Self-Healing This repository contains the complete raw physical testbed telemetry datasets, Jupyter Notebook analysis pipelines, plotting scripts, and ESP32 hardware deployment firmware from an experimental campaign evaluating the "TinyOL" framework on resource-constrained microcontrollers. The codebase and data validate an ultra-lightweight CUSUM-EWMA anomaly detection framework featuring an anti-poisoning state machine, coupled with a MAPE-K closed-loop self-healing controller to protect multi-modal IoT sensor reliability and multimedia Quality of Experience (QoE) during severe network congestion and DDoS floods. Note: An interactive, live web simulation of this mathematical framework is publicly accessible via GitHub Pages at: haranathrakshit.github.io/TinyOL-Simulation/. 📄 ASSOCIATED MANUSCRIPT This dataset and codebase support the findings presented in the research article: "Closed-Loop-TinyOL for Autonomic Anomaly Detection, Diagnosis, and Self-Healing in Edge IoT" 📂 REPOSITORY STRUCTURE TinyOL_Experiment/ │ ├── README.md (Main reproducibility documentation) │ ├── 01_Anomaly_Detection_CUSUM_EWMA/ (Stage 1 Anomaly Detection evaluation) │ ├── anomaly_analysis.py # Standalone script to calculate precision, recall, and bootstrap CIs │ ├── 01_Experiment_Scripts/ # ESP32 firmware (TinyOL_EdgeNode.ino) and receiver app (app.py) │ ├── 02_Raw_Datasets/ # Stochastic & deterministic raw telemetry CSVs │ ├── 03_Analysis_Notebooks/ # Step-by-step Jupyter notebooks for auditing & evaluation │ └── 04_Figures_and_Results/ # Pre-generated detection figures (HTOP, chaos, confusion matrix) │ └── 02_Adaptive_Self_Healing_MAPEK/ (Stages 2 & 3 Diagnostic and Healing evaluation) ├── 01_Experiment_Scripts/ # Telemetry plotting script (generate_healing_plots.py) ├── 02_Raw_Datasets/ # Baseline, Distance, and Congestion CSV datasets & serial logs └── 04_Figures_and_Results/ # Pre-generated self-healing telemetry and impact charts 📊 KEY TELEMETRY COLUMN DEFINITIONS L_t / true_latency_ms: Extracted physical MAC-layer transmission latency measured in milliseconds (ms). mu: The EWMA-based baseline mean calculated online directly on the microcontroller silicon. sigma: The EWMA-based mean absolute deviation. S_t: The TinyOL CUSUM Danger Score (accumulation of standardized deviations). State / inferred_state: The anti-poisoning state machine status (Normal, Warning, or Critical) or self-healing diagnosed condition (Baseline, Distance, Congestion). rssi: Received Signal Strength Indicator measured in dBm (used for diagnostic localization). 🛠 USAGE To audit the datasets, evaluate the anomaly detection thresholds, and automatically reproduce the classification metrics (e.g., 80.10% Precision), self-healing recovery benchmarks (e.g., **29.6% average latency reduction**, **45.6% variance reduction**), and figures found in the associated manuscript, navigate to the stage directories and run the analysis scripts: To run the anomaly detection sweep: cd 01_Anomaly_Detection_CUSUM_EWMA python anomaly_analysis.py To generate the self-healing telemetry and impact plots: cd 02_Adaptive_Self_Healing_MAPEK/01_Experiment_Scripts python generate_healing_plots.py Environment: Python 3.8+, Scikit-Learn, Pandas, Numpy, Matplotlib, Seaborn, Jupyter, Arduino IDE (v1.8+ or v2.x with ESP32 Core).