The rapid growth of Internet of Things (IoT) deployments has intensified the challenge of achieving reliable, secure, and energy-efficient operation under highly dynamic and non-stationary traffic conditions. In practical IoT networks, anomaly detection systems must simultaneously capture complex spatial–temporal dependencies while meeting strict constraints on inference latency and energy consumption at the edge. However, many existing approaches struggle to balance detection accuracy with operational efficiency, particularly when traffic patterns and attack behaviors evolve over time. In many real deployments, this evolution manifests as concept drift, where the statistical properties of network traffic gradually change, making fixed detection models and thresholds unreliable. To address these challenges, this paper presents a green and lightweight hybrid CNN–transformer architecture for adaptive anomaly detection in large-scale IoT networks. The proposed solution uses one-dimensional convolutional layers to explicitly capture localized cross-feature correlations and compress multivariate traffic representations before applying attention. This preliminary convolutional stage reduces noise, removes redundant temporal variations, and produces a compact representation, allowing the transformer to focus on meaningful temporal structure rather than raw high-dimensional inputs. Transformer encoders then model long-range temporal dependencies over these compact representations, enabling effective detection of both transient and persistent anomalies with reduced computational overhead. By combining convolutional compression with temporal attention, the model improves detection accuracy by jointly capturing short-range feature interactions and long-term behavioral evolution, while also reducing attention complexity and inference cost compared to transformer-only designs. To further enhance robustness under non-stationary conditions, an entropy-guided adaptive thresholding mechanism dynamically adjusts decision boundaries based on predictive uncertainty, allowing the system to maintain stable performance without retraining. Experiments on three representative IoT datasets and edge hardware show that the proposed approach achieves detection accuracy up to 97%, maintains average inference latency below 25 ms, and reduces energy consumption by about 27% compared to transformer-only baselines. Statistical analysis confirms that these improvements are significant (p<0.01) with large effect sizes (η2>0.15).
The integration of Digital Twins (DTs), blockchain, and Digital Product Passports (DPPs) is emerging as a promising direction for trustworthy, auditable, and interoperable industrial lifecycle management. However, an open issue is how heterogeneous lifecycle evidence generated by DTs from physical and industrial-system observations can be transformed into DPP-consumable claims while preserving provenance, integrity, temporal validity, and manageable certification costs. This paper proposes a framework for DPP-oriented dynamic certification of industrial DTs in distributed industrial environments. The proposed architecture connects physical assets, DT instances, off-chain evidence repositories, permissioned blockchain anchoring, and DPP interfaces. DTs derive structured lifecycle evidence from physical and industrial-system observations concerning products, components, materials, processes, and facilities; blockchain mechanisms provide tamper-evident anchoring through hashes, timestamps, signatures, and Merkle roots; and DPPs expose selected certified claims to authorized stakeholders. A parameterized discrete-event simulation evaluates DPP update policies, certification granularity, blockchain anchoring strategies, hierarchical lifecycle aggregation, and networked certification under heterogeneous IIoT and edge–cloud conditions. The results show that technical blockchain commit success alone is not sufficient to assess DPP feasibility: freshness lag, lifecycle coverage, on-chain payload, and energy cost must also be considered. Overall, the evaluation confirms that hybrid certification strategies can support scalable DT–Blockchain–DPP infrastructures by combining direct compact anchoring for critical lifecycle evidence with periodic, hierarchical, or Merkle-based aggregation for routine updates.
