http://repository.iiitd.edu.in/xmlui/handle/123456789/1795 Year-2026 Sun, 20 Sep 2026 13:32:12 GMT 2026-09-20T13:32:12Z http://repository.iiitd.edu.in/xmlui/handle/123456789/2097 Machine learning-driven timing analysis and physical design for VLSI Beniwal, Pooja; Saurabh, Sneha (Advisor) Electronic design automation (EDA) comprises software tools for designing modern integrated circuits that includes synthesis, placement, routing, timing analysis, and verification. As designs scale to billions of transistors, challenges arise from increased complexity, tighter timing margins, higher power–performance–area (PPA) demands, and long runtimes. Traditional EDA methods in VLSI design face several challenges due to their reliance on simplified analytical models and tuned heuristics. These ap- proaches often fail to capture complex, non-linear relationships among design parame- ters, resulting in limited accuracy. They are also computationally expensive and time- consuming because they depend on iterative optimization and repeated computation. As design complexity increases, traditional methods struggle to scale efficiently and require significant manual effort and expert intervention. Additionally, their ability to explore the design space is limited, often leading to suboptimal solutions, and they are less adaptable to variations and changing design conditions. Machine learning (ML) helps overcome these limitations by providing a data-driven approach that can model complex and high-dimensional relationships more efficiently. ML enables faster predic- tions compared to iterative methods, reducing computational cost and design time. It improves scalability for large and complex designs while minimizing the need for man- ual intervention. Furthermore, ML supports more efficient exploration of the design space and adapts better to variations, resulting in improved optimization and overall design quality. In the first part of this research, standard-cell modeling is made more accurate and robust by incorporating Multi-Input Switching (MIS) effects, which are ignored under the Single-Input Switching (SIS) assumption of traditional standard-cell library charac- terization. MIS can cause significant delay variations and glitches at the output, result- ing in inaccurate timing analysis, hold-time violations, signal integrity issues, increased power consumption, and incorrect sequential behavior. A novel satisfiability(SAT)- guided, ML-driven MIS characterization framework is proposed for multi-input combi- national standard cells. First, a logical analysis of the Boolean function of a given logic gate is performed to identify input patterns that can lead to MIS-induced speed-up or glitches. MIS-relevant patterns are extracted by formulating a SAT problem such that the satisfiable instances are the relevant input combinations. For each identified pattern, data is collected through SPICE simulations to capture the impact of MIS on timing attributes and glitches. This data is then used to develop an augmented technology li- brary that accurately captures MIS effects by leveraging ML techniques. Subsequently, MIS-aware STA is performed using traditional STA tool coupled with the augmented technology library. Further, to streamline the entire process of pattern extraction, data generation, and augmented library creation, an automated tool framework named LiMo (Library Model), is developed in this work. This framework integrates a SAT solver, a SPICE simulator, dataset optimization strategies, ML training/testing infrastructure, and multiprocessing capabilities to create MIS-aware augmented timing libraries. The proposed framework is validated through experimental results on ISCAS benchmark circuits. In delay calculation of multi-input combinational cells, ignoring MIS leads to Relative Root Mean Square Error (RRMSE) exceeding 40% compared to golden SPICE results, whereas LiMo-generated libraries achieve RRMSE below 7% compared to golden SPICE. For predicting the attributes of the MIS-induced glitches, employing the augmented libraries model deliver RRMSE less than 6%. Moreover, computation using augmented libraries is 10,000 × faster than the SPICE simulation. Hence, the proposed methodology can be employed in MIS-aware timing analysis for industrial designs. Building on advances in combinational standard-cell characterization, limitations of conventional timing models of sequential elements are addressed in this work. In traditional approaches, setup time (ST), hold time (HT), and clock-to-Q (C2Q) delays are modeled independently using two-dimensional lookup tables. Such a deterministic and decoupled representation fails to capture their interdependence, thereby introduc- ing pessimism that results in artificial violations and unnecessary design iterations. To address these limitations, a novel statistical, ML-driven characterization framework is proposed, in which fixed timing constraints are replaced with a probabilistic formula- tion. Instead of explicitly modeling ST and HT, an ML-based latch prediction model is proposed to estimate the probability of correct data latching under multidimensional operating conditions, including setup/hold skews and process variations. Through this approach, complex parameter dependencies are learned, and a safe operating region is defined within an extended timing space. In addition, a second ML model is developed for the prediction of C2Q delay within this extended timing region, ensuring accu- rate delay estimation even beyond conventionally defined timing constraints. Unlike traditional characterization methods, which assume fixed timing arcs, continuous and context-aware delay modeling is enabled under near-critical conditions. A hierarchi- cal violation-waiver framework is proposed to ensure that violations are safely waived. Along with latching probability, it is verified that the extension of the timing space does not introduce issues for flip-flops that were already operating safely under traditional timing constraint. The proposed framework is validated using TAU benchmark circuits in 45 nm technology and is verified against Monte Carlo SPICE simulations. Experi- mental results demonstrate 100% precision in filtering marginal violations, with no false positives, while maintaining C2Q delay prediction errors below 2% when compared to golden SPICE values within the extended timing region. In the final phase of this research, the focus shifts toward extending the application of machine learning techniques to address inaccuracies in congestion estimation dur- ing placement. Conventional early global routing (eGR) techniques, widely used for congestion-aware placement, rely on simplified models that fail to capture fine-grained variations in routing demand caused by cell dimensions, pin density, and local layout structures. This results in a mismatch with global routing (GR), leading to subopti- mal placement decisions and degraded routing closure.To address this, an ML-driven congestion prediction and alleviation framework is proposed, leveraging the ability of ML to learn complex, high-dimensional relationships between placement features and routing demand. Instead of invoking a routing engine, the model predicts congestion di- rectly from design features-including newly proposed features that capture local struc- tural and pin-access characteristics, thereby enabling fast and accurate estimation. A placement-modification method is also introduced to alleviate predicted congestion hot spots, and its effectiveness is demonstrated through loose integration with an industrial place-and-route (PnR) tool, thereby enabling more robust and congestion-aware physi- cal design flows. The proposed technique is evaluated on ISPD 2014/2015 benchmark designs and validated against golden global routing congestion obtained from a com- mercial PnR tool. An RMSE reduction of 68% in congestion prediction is achieved by the ML model compared to early global routing estimates, and an 8-30% reduction in routing congestion is enabled through improved optimization. Sat, 01 Aug 2026 00:00:00 GMT http://repository.iiitd.edu.in/xmlui/handle/123456789/2097 2026-08-01T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/1986 Design, modeling, and optimization of hybrid LiFi-WiFi networks for high-performance indoor wireless communication Paramita, Saswati; Bohara, Vivek Ashok (Advisor); Srivastava, Anand (Advisor) The exponential growth of bandwidth-intensive applications such as ultra-high definition (UHD) video streaming, cloud computing, augmented and virtual reality (AR/VR), and the Internet of Things (IOT) has pushed existing wireless communication technologies to their limits. Conventional RF-based networks, such as Wi-Fi and LTE, are increasingly strained by spectrum scarcity and escalating user demands. This has spurred interest in alternative or complementary communication paradigms capable of delivering higher data rates, lower latency, improved security, and better energy efficiency. Light Fidelity (Li-Fi), operating within the visible light spectrum, has emerged as a promising candidate for next-generation indoor wireless systems. Leveraging existing lighting infrastructure, Li-Fi offers vast unlicensed bandwidth, inherent security through confined coverage, and high potential data rates. However, despite these advantages, Li-Fi faces significant deployment challenges—most notably limited coverage, susceptibility to line-of-sight (LOS) blockages, sensitivity to device orientation, and degraded performance in high mobility scenarios. Furthermore, existing MAC-Iayer protocols in Li-Fi often borrow from Wi-Fi standards, such as CSMA/CA, which are not fully optimized for the unique characteristics of visible light communication (VLC) networks. The initial stage of this research addressed MAC-Iayer inefficiencies in heterogeneous Li-Fi environments. A hybrid CSMA/CA—HCCA uplink MAC protocol was developed to dynamically switch between contention-based and contention-free modes depending on device types and network load, significantly improving throughput, delay, and collision probability in diverse traffic scenarios [1]. While this approach enhanced medium access efficiency, it did not fully address performance degradation caused by user mobility and dynamic channel conditions. To tackle mobility-induced challenges, an Orientation-Aware Multi-AP Li-Fi Network (OAM-LiFiNet) was proposed [2]. This framework leveraged real-time SINR measurements and channel metrics to dynamically adjust device orientation, thereby mitigating interference and improving throughput under user movement. Although effective, Li-Fi's dependence on LOS links meant that the system remained vulnerable to blockage events caused by static obstacles or transient movement within the environment. Recognizing the importance of blockage modeling, the research introduced FixOM and SAM [3], two novel approaches for quantifying the impact of obstacles in Li-Fi environments. FixOM modeled stationary obstructions using geometric analysis, while SAM incorporated both complete and partial shadowing effects for a more realistic performance representation. These models provided valuable insights for Li-Fi deployment planning but also highlighted that blockage mitigation within a pure Li-Fi framework could not entirely eliminate service interruptions. This realization motivated the transition toward hybrid Li-Fi/Wi-Fi networks (HLWNs), which combine Li-Fi's high-speed links with Wi-Fi's broader coverage and robustness. Prototype testbeds were developed [4, 5] to evaluate hybrid systems in realistic indoor scenarios, demonstrating superior throughput, handover performance, and service continuity compared to standalone technologies. While hybrid networks improved coverage and throughput, modern MU-MIMO Wi-Fi still suffered from one significant drawback—the high overhead of channel state information (CSI) feedback. This feedback is essential for spatial multiplexing but consumes substantial wireless resources, reducing spectral efficiency and limiting achievable throughput, especially in dense multi-user scenarios. In this thesis, this disadvantage is addressed by utilizing LiFi links to carry CSI feedback through the proposed WiLiConnect and WiLiConnect-Opt systems [6, 7]. By offloading CSI transmission to Li-Fi access points, Wi-Fi capacity is freed for user data, drastically reducing overhead and substantially improving sum-rate performance in hybrid deployments. Building on this foundation, the research advanced to link aggregation and mobilityaware resource allocation strategies for HLWNs. The final stage of the research focused on advanced link aggregation algorithms—LA-SINR, LA-EQ0S, and FLADA [8, maximized combined Li-Fi/Wi-Fi throughput while meeting QoS and fairness requirements. These were complemented by a mobility-aware handover optimization strategy [10] that used a two-stage approach: offline linear programming for static users and a search-space pruning mechanism with re-optimization for mobile users near AP borders. Analytical modeling of outage probabilities [11] in LA-enabled HLWNs further validated their superior robustness compared to standalone networks. Through these interconnected contributions, this thesis presents a holistic, multi-layered framework for high-capacity, mobility-friendly indoor networks. By starting from MAC-Iayer improvements in standalone Li-Fi, addressing mobility and blockage, overcoming Wi-Fi's CSI feedback bottleneck via Li-Fi, integrating hybrid Li-Fi/WiFi architectures, and culminating in advanced link aggregation and handover optimization, the research provides a comprehensive roadmap for deploying next-generation indoor wireless systems that meet the evolving demands of smart homes, offices, and industrial environments. Mon, 01 Jun 2026 00:00:00 GMT http://repository.iiitd.edu.in/xmlui/handle/123456789/1986 2026-06-01T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/1825 Inverse synthetic aperture radar imaging of automotive targets Pandey, Neeraj; Ram, Shobha Sundar (Advisor) Advanced driver assistance systems (ADAS) aim to improve road safety, reduce fatalities, and enable autonomous driving. Modern vehicles rely on multiple sensors such as lidar, cameras, thermal detectors, and radar to detect and classify road users. Among these, millimeter-wave automotive radars offer robust range and velocity estimation, all-weather operation, and unobtrusive bumper integration. High-resolution two-dimensional radar images, and in particular inverse synthetic aperture radar (ISAR) images, can provide detailed information on target size, shape, and motion. However, existing ISAR studies of ground vehicles at automotive radar frequencies have produced only limited datasets for a few targets under controlled conditions, and these datasets are not publicly available. As a result, there is a lack of realistic, large-scale ISAR data suitable for modern machine learning (ML) algorithms for automotive applications. This thesis develops a framework for simulating high-fidelity ISAR images of automotive targets at millimeter-wave (mm-wave) frequencies. The simulation model incorporates vehicle kinematics, radar scattering phenomenology, range–Doppler clutter, and receiver noise for a 77 GHz automotive radar. Static and dynamic mm-wave clutter for automotive scenarios is modelled using measurements acquired on Indian roads, taking into account different surface types and roughness conditions. The resulting clutter statistics are used to parameterise phenomenological clutter models in the simulator. The framework is validated qualitatively and quantitatively against measurement data gathered from real automotive radars. The simulated ISAR images are then used as inputs to traditional ML classifiers and deep neural networks for the classification of automotive targets; the results show that ISAR radar images are excellent features for accurately classifying different road vehicles. The thesis further investigates the reliability and interpretability of these classification decisions. It is shown that misclassifications can occur even when noise and clutter are relatively low. To analyse such cases, a method based on counterfactual explanations is proposed, using generative adversarial networks (GANs) to perturb ISAR images of a query class until they are classified as a distractor class, while enforcing that the perturbations remain realistic and consistent with the original class distribution. The resulting counterfactual images provide physics-based insight into which target regions and micro-Doppler features drive the classifier’s decisions. Finally, two application-oriented studies using ISAR images are presented: (i) an automated parking test framework in which an externally mounted radar generates high-resolution images of a car parking in a designated slot and a polynomial trajectory fit is used to assess parking performance; and (ii) an around-the-corner radar (ACR) proof-of-concept at 77 GHz for non-line-of-sight collision avoidance, where sparsity-based dictionary learning is used to separate overlapping range–Doppler returns and reconstruct the signatures of multiple dynamic targets in an urban NLOS configuration Sun, 01 Feb 2026 00:00:00 GMT http://repository.iiitd.edu.in/xmlui/handle/123456789/1825 2026-02-01T00:00:00Z