Open Access

ARTICLE

A Bilevel Deep Learning Optimization Framework for Joint Energy Harvesting Prediction and Energy-Aware Scheduling in IoT-Based Wireless Sensor Networks

Mohammad Q. Al-Jamal¹, Mahmoud Al Jamal², Bashar S. Khassawneh^3,*, Ayoub Alsarhan^4,5, Amina Salhi⁶, Tahani Alsubait⁷

1 Department of Renewable Energy, Jadara University, Irbid, Jordan
2 Department of Cybersecurity, Irbid National University, Irbid, Jordan
3 Department of Computer Science, College of Information Technology, Amman Arab University, Amman, Jordan
4 Faculty of Information Technology, Al-Ahliyya Amman University, Amman, Jordan
5 Department of Information Technology, Faculty of Prince Al-Hussien bin Abdullah, The Hashemite University, Zarqa, Jordan
6 Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia
7 Department of Computer Science and Artificial Intelligence, Umm Al-Qura University, Makkah, Saudi Arabia

* Corresponding Author: Bashar S. Khassawneh. Email:

Computers, Materials & Continua 2026, 88(3), 38 https://doi.org/10.32604/cmc.2026.079984

Received 01 February 2026; Accepted 22 April 2026; Issue published 23 July 2026

Abstract

Energy sustainability and secure operation are persistent challenges in Internet-of-Things (IoT) wireless sensor networks (WSNs), where limited battery capacity, heterogeneous traffic, and security procedures jointly drive premature node depletion and service degradation. This paper proposes an uncertainty-aware bilevel co-optimization framework that unifies residual-energy prediction with robust, energy-aware scheduling for clustered IoT-WSNs. At the lower level, a lightweight temporal predictor (TCN + LSTM with stochastic sampling) learns short-horizon residual-energy evolution from multivariate, dataset-aligned windows capturing sensing/communication activity, proximity-to-cluster-head effects, and security overhead (authentication latency, key exchange, and rekeying), and produces both point forecasts and uncertainty estimates to enable risk-sensitive control. At the upper level, a constrained, horizon-based scheduler selects per-node actions (duty cycle, sensing rate, transmission power) to extend network lifetime and balance residual energy while enforcing safety thresholds and operational bounds; bilevel coupling is realized via differentiable hypergradient updates, complemented by trust-region action smoothing and adaptive primal–dual constraint handling to suppress energy-critical states under uncertainty. On a real-world WSN energy–security dataset, the proposed model attains the best lower-level learning performance with MAE=0.004, RMSE=0.006, and R2=0.995 for residual-energy regression, and up to 0.98 accuracy/0.98 F1 for secure-and-efficient classification. End-to-end scheduling results show that the full framework improves estimated network lifetime by up to 1.60×, reduces residual-energy variance to 0.60×, and lowers safety violations to 0.35× relative to a fixed-policy baseline, demonstrating robust, secure, and sustainable IoT-enabled WSN operation.

---

Keywords

---