@Article{cmc.2026.079984,
AUTHOR = {Mohammad Q. Al-Jamal, Mahmoud Al Jamal, Bashar S. Khassawneh, Ayoub Alsarhan, Amina Salhi, Tahani Alsubait},
TITLE = {A Bilevel Deep Learning Optimization Framework for Joint Energy Harvesting Prediction and Energy-Aware Scheduling in IoT-Based Wireless Sensor Networks},
JOURNAL = {Computers, Materials \& Continua},
VOLUME = {},
YEAR = {},
NUMBER = {},
PAGES = {{pages}},
URL = {http://www.techscience.com/cmc/online/detail/27188},
ISSN = {1546-2226},
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 <i>uncertainty-aware bilevel co-optimization framework</i> 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 <mml:math id="mml-ieqn-1"><mml:mrow><mml:mi mathvariant="normal">M</mml:mi><mml:mi mathvariant="normal">A</mml:mi><mml:mi mathvariant="normal">E</mml:mi></mml:mrow><mml:mo>=</mml:mo><mml:mn>0.004</mml:mn></mml:math>, <mml:math id="mml-ieqn-2"><mml:mrow><mml:mi mathvariant="normal">R</mml:mi><mml:mi mathvariant="normal">M</mml:mi><mml:mi mathvariant="normal">S</mml:mi><mml:mi mathvariant="normal">E</mml:mi></mml:mrow><mml:mo>=</mml:mo><mml:mn>0.006</mml:mn></mml:math>, and <mml:math id="mml-ieqn-3"><mml:msup><mml:mi>R</mml:mi><mml:mn>2</mml:mn></mml:msup><mml:mo>=</mml:mo><mml:mn>0.995</mml:mn></mml:math> for residual-energy regression, and up to <mml:math id="mml-ieqn-4"><mml:mn>0.98</mml:mn></mml:math> accuracy/<mml:math id="mml-ieqn-5"><mml:mn>0.98</mml:mn></mml:math> F1 for secure-and-efficient classification. End-to-end scheduling results show that the full framework improves estimated network lifetime by up to <mml:math id="mml-ieqn-6"><mml:mn>1.60</mml:mn><mml:mo>×</mml:mo></mml:math>, reduces residual-energy variance to <mml:math id="mml-ieqn-7"><mml:mn>0.60</mml:mn><mml:mo>×</mml:mo></mml:math>, and lowers safety violations to <mml:math id="mml-ieqn-8"><mml:mn>0.35</mml:mn><mml:mo>×</mml:mo></mml:math> relative to a fixed-policy baseline, demonstrating robust, secure, and sustainable IoT-enabled WSN operation.},
DOI = {10.32604/cmc.2026.079984}
}