The proliferation of 5G technology presents an unprecedented challenge in managing the energy consumption of densely deployed network infrastructures, particularly Base Stations (BSs), which account for the majority of power usage in mobile networks. The O-RAN architecture, with its emphasis on open and intelligent design, offers a promising framework to address the Energy Efficiency (EE) demands of modern telecommunication systems. This paper introduces two xApps designed for the O-RAN architecture to optimize power savings without compromising the Quality of Service (QoS). Utilizing a commercial RAN Intelligent Controller (RIC) simulator, we demonstrate the effectiveness of our proposed xApps through extensive simulations that reflect real-world operational conditions. Our results show a significant reduction in power consumption, achieving up to 50% power savings with a minimal number of User Equipments (UEs), by intelligently managing the operational state of Radio Cards (RCs), particularly through switching between active and sleep modes based on network resource block usage conditions.

Deep Reinforcement Learning (DRL) emerges as a prime solution for Unmanned Aerial Vehicle (UAV) trajectory planning, offering proficiency in navigating high-dimensional spaces, adaptability to dynamic environments, and making sequential decisions based on real-time feedback. Despite these advantages, the use of DRL for UAV trajectory planning requires significant retraining when the UAV is confronted with a new environment, resulting in wasted resources and time. Therefore, it is essential to develop techniques that can reduce the overhead of retraining DRL models, enabling them to adapt to constantly changing environments. This paper presents a novel method to reduce the need for extensive retraining using a double deep Q network (DDQN) model as a pre-trained base, which is subsequently adapted to different urban environments through Continuous Transfer Learning (CTL). Our method involves transferring the learned model weights and adapting the learning parameters, including the learning and exploration rates, to suit each new environment's specific characteristics. The effectiveness of our approach is validated in three scenarios, each with different levels of similarity. CTL significantly improves learning speed and success rates compared to DDQN models initiated from scratch. For similar environments, Transfer Learning (TL) improved stability, accelerated convergence by 65%, and facilitated 35% faster adaptation in dissimilar settings.

Abstract The Generalized Feistel Structure ( $$\texttt{GFS}$$ GFS ) is one of the most widely used frameworks in symmetric cipher design. In FES 2010, Suzaki and Minematsu strengthened the cryptanalysis security of $$\texttt{GFS}$$ GFS by searching for shuffles with the best diffusion property. In ASIACRYPT 2018, Shi et al. suggested a set of shuffles, which makes $$\texttt{GFS}$$ GFS a better resistance against Demirci–Selcuk meet-in-the-middle cryptanalysis. Since these shuffles are different from the currently known good ones and also different from the shuffles used in $$\texttt{TWINE}$$ TWINE and $$\texttt{LBlock}$$ LBlock , our research focuses on a more comprehensive evaluation of $$\texttt{GFS}$$ GFS with different shuffles, including diffusion property of shuffle, differential, linear, impossible differential, zero-correlation linear, integral and Demirci–Selcuk meet-in-the-middle cryptanalysis, to find the best one. Such evaluations entail significant time consumption. Thus, we utilize Mixed Integral Linear Programming models and introduce an evaluate-and-filter strategy to achieve it efficiently. Our results verify that the shuffles discovered by Suzaki and Minematsu and those used in $$\texttt{TWINE}$$ TWINE and $$\texttt{LBlock}$$ LBlock are the best so far. We also find that the cryptanalysis resistances of $$\texttt{GFS}$$ GFS are not necessarily consistent. It is this finding that makes the necessity of our more comprehensive evaluation self-evident.