Fortifying Industry 4.0 Solar Power Systems: A Blockchain-Driven Cybersecurity Framework with Immutable LightGBM

This paper presents a novel blockchain-embedded cybersecurity framework for industrial solar power systems, integrating immutable machine learning (ML) with distributed ledger technology. Our contribution focused on three factors, Quantum-resistant feature engineering using the UNSW-NB15 dataset adapted for solar infrastructure anomalies. An enhanced Light Gradient Boosting Machine (LightGBM) classifier with blockchain-validated decision thresholds, and A cryptographic proof-of-threat (PoT) consensus mechanism for cyber attack verification. The proposed Immutable LightGBM model with majority voting and cryptographic feature encoding achieves 96.9% detection accuracy with 0.97 weighted average of precision, recall and F1-score, outperforming conventional intrusion detection systems (IDSs) by 12.7% in false positive reduction. The blockchain layer demonstrates a 2.4-s average block confirmation time with 256-bit SHA-3 hashing, enabling real-time threat logging in photovoltaic networks. Experimental results improve in attack traceability compared to centralized security systems, establishing new benchmarks for trustworthy anomaly detection in smart grid infrastructures. This study also compared traditional and hybrid ML based blockchian driven IDSs and attained better classification results. The proposed framework not only delivers a resilient, adaptable threat mitigation system (TMS) for Industry 4.0 solar powered infrastructure but also attains high explainability, scalability with tamper-proof logs, and remarkably exceptional ability of endurance to cyber attacks.