http://hdl.handle.net/123456789/10317 2026-06-25T15:49:48Z http://hdl.handle.net/123456789/21311 5G to 6G Inclusion of Edge Computing and AI-Native Computing Hajra Rizwan, 01-133222-022 This work intends to leverage simulation techniques to get knowledge regarding the designing and analysis of wireless communication networks. The parameters, for instance, throughput, Signal-to-Noise Ratio, and latency among others are used to compare the efciency of 5G networks against that of 6G. The main aim of this work is to evaluate the advantages of next generation communication networks over the present one. As such, this work starts with the theoretical framework of wireless communication systems, specifcally the development from 5G towards 6G technology and the need for complex network optimization techniques in this process. This wireless communication system has been designed in a hierarchical form that consists of fve layers namely; user equipment, base station, wireless channel, edge computing, and 6G AI. In essence, this is a powerful design concept since it allows the simulation of real-life communication behavior. Given its ability to perform computations and visualization, the MATLAB software becomes the preferred simulation tool here. The modules include initialization, channel modeling, computation of performance parameters, and output visualization. Path loss computation, received signal power calculation, calculation of SNR, throughput computation. In order to ensure uniformity of comparative analysis, these steps are performed in various practiced environments. AI-based optimization in 6G network is illustrated apart from modeling communication normally done in practice. Some of these include improved SNR performance, throughput adaptability, reduced latencies, and efcient use of resources. It also incorporates theoretical measures such as security and data handling practices. The process of testing and evaluation reveals the differences between the 5G system and 6G system under identical conditions. When comparing these two technologies based on the throughput, SNR, and latency, one can observe that 6G outperforms 5G in all aspects. Additionally, the use of edge computing and AI optimization enhances their performance. The work successfully demonstrates how theoretical models can be ivtransformed into simulations. It has been analyzed that the sixth generation of wireless communication technology is far superior to its predecessor, especially with regard to providing faster, intelligent, and low latency networks for future applications. Supervised by Dr. Imtiaz Alam 2026-01-01T00:00:00Z http://hdl.handle.net/123456789/21249 Antenna/Radar Positioning System for Enhanced Military Communication Asma Kausar, 01-133222-011; Aneela Kousar, 01-133222-009 Reliable communication is a fundamental requirement in modern military operations, particularly in dynamic and unpredictable battlefeld environments where mobility, obstruction, and environmental interference severely degrade signal quality. Conventional static antenna systems are often unable to maintain optimal alignment under such conditions, leading to reduced signal strength, unstable connectivity, and limited operational effectiveness. To address these challenges, this project presents the design and implementation of an Adaptive Antenna Positioning System based on Infrared (IR) sensing for enhanced communication reliability. The proposed system employs a two-axis motorized antenna mount capable of automatic azimuth and elevation control. Instead of relying on RF signal strength estimation, the system utilizes Infrared (IR) transmitter–receiver modules to determine directional alignment with the signal source. The IR-based sensing mechanism continuously detects the intensity and directionality of incoming infrared signals, enabling the system to identify the optimal orientation for maximum alignment accuracy. A microcontroller-based control unit processes real-time IR sensor data and dynamically adjusts the antenna position using high-precision stepper motors, ensuring smooth and accurate tracking performance. To evaluate system performance under controlled dynamic conditions, a custom-built moving IR signal source mechanism is developed to simulate mobility scenarios. The hardware architecture integrates IR sensing modules, an Arduino-based control system, motor driver circuits, and a wireless monitoring interface for real-time observation and testing. This integrated design allows effective validation of tracking behavior in both static and dynamic environments. Experimental results demonstrate that the proposed IR-based system achieves improved directional accuracy, stable alignment, and reduced signal deviation compared to conventional fxed antenna setups. The system shows reliable tracking capability under simulated movement conditions, confirming its suitability for controlled short-range adaptive communication applications. Overall, the project contributes to the development of intelligent antenna positioning systems by integrating IR sensing technology with embedded control and electromechanical actuation. The resulting framework offers a cost-effective, lightweight, and scalable solution that can serve as a foundation for further advancements in adaptive communication and tracking systems. Supervised by Dr. Nadia Sultan 2026-01-01T00:00:00Z http://hdl.handle.net/123456789/21250 AI Powered Dynamic Control System and Efficiency Optimization for Steam Turbine Rawal Khan, 01-133222-064; Muhammad Sufian, 01-133222-056 Steam turbines are the key elements of thermal power plants. Their efcient functioning is vital for optimizing power production and minimizing operational expenses. But the turbine performance is continuously changing with changing thermodynamic conditions namely main steam pressure, main steam temperature, cold reheat pressure and cold reheat temperature. Traditional industrial control systems such as PID and DCS guarantee the stability of operations, but they are not designed for intelligent optimization of efciency of the operations in the dynamic operating environment. In this work, a physics aware reinforcement learning based supervisory optimization framework is presented for HP steam turbine efciency improvement. The proposed system is a closed loop supervisory architecture combining thermodynamic efciency estimation, reinforcement learning optimization, recommendation evaluation and real-time dashboard visualization. The HP turbine efciency is calculated by thermodynamic relations based on the change in enthalpy of the steam and the calculated efciency is checked with the dataset efciency values for physical consistency and reliability. Three reinforcement learning algorithms (PPO, SAC, and TD3) are trained to provide safe operational recommendations via controlled modifcations in selected thermodynamic operating parameters. Prior to presenting recommendations to the operator, the expected turbine efciency is re-evaluated after each recommended action using the physics-based effciency model. The reinforcement learning models are also compared with No Action and Random Action baseline strategies in terms of efciency improvement and statistical evaluation metrics. A real-time supervisory dashboard is also developed to visualize the current HP turbine efficiency, recommended operational changes, expected optimized efciency, and efciency improvement. The proposed framework also enables real-time data ingestion from an external system that allows live monitoring and recommendation generation in dynamic operating conditions. The system developed serves as a supervisory advisory layer, not interfering directly with the existing industrial PID/DCS infrastructure. The proposed framework demonstrates the potential of the combination of thermodynamic modeling and reinforcement learning to develop intelligent, adaptive, and safe supervisory optimization systems for steam turbine efficiency improvement in modern thermal power plants. Supervised by Dr. Nadia Sultan 2026-01-01T00:00:00Z http://hdl.handle.net/123456789/21253 Battery Pack Cell Balancing and Diagnosis Device for Electric Bikes Muhammad Abdullah, 01-133222-042; Hassan Waheed, 01-133222-026 Electric bikes commonly utilize Lithium Iron Phosphate (LiFePO4) battery packs composed of multiple cells connected in series to achieve high voltage requirements, where the overall performance, safety, and lifespan depend heavily on the equilibrium of individual cells. A single weak or degraded cell can significantly reduce the overall capacity and reliability of the entire pack, yet professional cell-level diagnostic equipment remains expensive and inaccessible to local workshops and general EV users in Pakistan. This project presents a low-cost, discrete component-based Passive Battery Cell Balancing and Diagnostic Device designed specifically for a battery configuration. Unlike active balancing systems that require complex energy transfer components, this system utilizes a switched shunt resistor technique to dissipate excess energy from higher-voltage cells through power resistors, ensuring all cells reach a uniform state of charge. The device performs comprehensive diagnostics by monitoring real-time voltage and status through an analog control logic powered by NE555 timers and Darlington pair drivers. By enabling precise detection and balancing of cells through manual threshold tuning, the proposed solution prevents unnecessary full-pack replacements, making EV maintenance more economical and sustainable. Portable, user-friendly, and locally manufacturable using readily available electronic components, this device offers an affordable alternative to industrial-grade analyzers and directly supports the growing electric vehicle ecosystem. Supervised by Dr. Asad Waqar 2026-01-01T00:00:00Z