Code clones are a well-known source of technical debt, often degrading software maintainability. Modern AI coding assistants can unintentionally introduce clones or even licenseincompatible code, posing maintenance and legal challenges. This research proposes a Large Language Model (LLM)-powered clone refactoring assistant that proactively detects duplicative code during development and suggests high-level refactorings. By bridging traditional clone detection with LLM-driven code generation or transformation, the approach aims to remove redundancies early while ensuring changes remain behavior preserving and legally compliant. The assistant will integrate into development workflows to prevent clone propagation, flag potential intellectual property risks, and incorporate developer feedback for explainable, trustworthy operation. We will evaluate its impact on code quality and developer productivity, and assess how AI enhancements influence long-term maintenance efforts.

The growing demand for computation-intensive artificial intelligence (AI) and machine learning (ML) applications necessitates carbon-neutral edge computing to enhance resource efficiency, reduce energy consumption, and promote sustainability in Industrial Internet of Things (IIoT) systems. However, reducing service latency and energy consumption while ensuring execution accuracy and a predictable carbon footprint and its associated cost remains a critical research challenge. Existing works in the literature experience significant challenges for task offloading due to a lack of edge collaboration and ineffective management of Carbon Emission Rights (CER) credits. In this paper, we have developed an optimization framework leveraging Mixed Integer Linear Programming (MILP), namely GRELMON, to jointly minimize service latency and energy consumption while maximizing task accuracy in carbon-neutral collaborative edge and cloud computing for IIoT environments. Moreover, a carbon emission forecasting model using a hybrid deep learning approach is also developed to prevent unnecessary CER purchases. The experimental results demonstrate that GRELMON outperforms state-of-the-art methods by reducing latency and energy consumption while improving the accuracy of the execution of ML tasks.

The Internet of Medical Things (IoMT) has emerged as a transformative technology platform in the healthcare sector, enabling real-time monitoring and intelligent decision-making through connected devices. However, prioritizing and offloading the massive volume of computational tasks generated by IoMT devices while minimizing latency and energy consumption poses significant challenges. Existing approaches often overlook dynamic real-time factors such as task urgency and data freshness, as well as the integration of local task processing via Device-to-Device (D2D) communication with offloading to Mobile Edge Computing (MEC) servers. In this paper, we develop a priority- and Age of Information (AoI)-Aware task offloading framework for latency and energy optimization in healthcare IoT systems, namely PRALEIT, exploiting Mixed Integer Linear Programming (MILP) problem. The developed PRALEIT system introduced probabilistic classification of IoMT tasks based on vital signs and AoI value by leveraging a Bayesian classifier. The experimental results depict that the PRALEIT system significantly reduces task execution delay and energy consumption compared to state-of-the-art models, ensuring reliable and sustainable healthcare services.

Efficient deployment of a service function chain (SFC) on virtual network functions (VNFs) and their mapping to virtual machines (VMs) in 5G networks is highly important to reduce user application service latency as well as to minimize the cost of VM migration. Existing works in the literature have either considered service latency or migration cost while deploying an SFC on VMs. In this paper, the problem of dynamically mapping VNFs running a SFC to different virtual machines in a 5G network has been formulated as a multi-objective linear Programming (MOLP) problem. The developed optimization model, namely Trade-Lcm, minimizes user application service latency while reducing the cost of migrating virtual network functions associated with an SFC. The numerical performance analysis results demonstrate a significant improvement in minimizing service latency of user applications and cost of VM migration as high as 30% and 10%, respectively, compared to the state-of-the-art work.

Mobile Device Cloud (MDC) is a promising and lucrative cloud environment that uses the idle resources of nearby mobile devices to improve the performance of compute-intensive applications. By computing code on nearby devices instead of a distant master cloud, the MDC system can improve the performance of real-time applications. It is challenging for the MDC system to efficiently use the resources because of cost and QoE. While allocating high-quality resources to mobile applications might be effective in decreasing the latency, it will increase the cost, and the allocation of low-quality resources will increase execution latency, diminishing the quality of experience (QoE) of the users. The works in the literature didn't come up with methods of trading off these two conflicting objectives in a fair way. In this paper, we present an optimization framework, namely QCMDC, for allocating tasks in an MDC environment, which brings a trade-off between maximizing users' QoE and minimizing the execution cost of the worker devices. Empirical evaluations have been carried out in Python and the results demonstrate significant performance improvement in terms of QoE and execution cost compared to other state-of-the-art works.