Related papers: Traffic-aware Threshold Adjustment for NFV Scaling…

Dynamic routing in software-defined networking (SDN) can be viewed as a centralized decision-making problem. Most of the existing deep reinforcement learning (DRL) agents can address it, thanks to the deep neural network (DNN)incorporated.…

Convolutional Neural Networks have dramatically improved in recent years, surpassing human accuracy on certain problems and performance exceeding that of traditional computer vision algorithms. While the compute pattern in itself is…

Chip placement, a critical step in the VLSI physical design flow, directly impacts performance, power, and routability. Traditional chip placement methods, relying on analytical optimization or sequential reinforcement learning (RL), face…

Given the great threat of adversarial attacks against Deep Neural Networks (DNNs), numerous works have been proposed to boost transferability to attack real-world applications. However, existing attacks often utilize advanced gradient…

Flow-matching-based policies have recently emerged as a promising approach for learning-based robot manipulation, offering significant acceleration in action sampling compared to diffusion-based policies. However, conventional flow-matching…

Intensified netload uncertainty and variability led to the concept of a new market product, flexible ramping product (FRP). The main goal of FRP is to enhance the generation dispatch flexibility inside real-time (RT) markets to mitigate…

The area of mobile ad hoc networking has received considerable attention of the research community in recent years. These networks have gained immense popularity primarily due to their infrastructure-less mode of operation which makes them…

Diffusion Policy is a powerful technique tool for learning end-to-end visuomotor robot control. It is expected that Diffusion Policy possesses scalability, a key attribute for deep neural networks, typically suggesting that increasing model…

We study behavior-regularized reinforcement learning (RL), where regularization toward a reference distribution (the dataset in offline RL or the base model in LLM RL finetuning) is essential to prevent value over-optimization caused by…

The growing demand for services and the rapid deployment of virtualized network functions (VNFs) pose significant challenges for achieving low-latency and energy-efficient orchestration in modern edge-core network infrastructures. To…

Many reasons make NFV an attractive paradigm for IT security: lowers costs, agile operations and better isolation as well as fast security updates, improved incident responses and better level of automation. At the same time, the network…

With the sharp growth of cloud services and their possible combinations, the scale of data center network traffic has an inevitable explosive increasing in recent years. Software defined network (SDN) provides a scalable and flexible…

All data on the Internet are transferred by network traffic, thus accurately modeling network traffic can help improve network services quality and protect data privacy. Pretrained models for network traffic can utilize large-scale raw data…

We all depend on mobility, and vehicular transportation affects the daily lives of most of us. Thus, the ability to forecast the state of traffic in a road network is an important functionality and a challenging task. Traffic data is often…

In this note, we propose a case study of freeway traffic flow modeled as a hybrid system. We describe two general classes of networks that model flow along a freeway with merging onramps. The admission rate of traffic flow from each onramp…

Deep neural networks (DNNs) have emerged as a dominant approach for developing traffic forecasting models. These models are typically trained to minimize error on averaged test cases and produce a single-point prediction, such as a scalar…

Forwarding decisions in classical IP-based networks are predetermined by routing. This is necessary to avoid loops, inhibiting opportunities to implement an adaptive and intelligent forwarding plane. Consequently, content distribution…

Network Functions Virtualization (NFV) and Software-Defined Networking (SDN) are new paradigms in the move towards open software and network hardware. While NFV aims to virtualize network functions and deploy them into general purpose…

Deep neural networks (DNNs) have been widely applied in diverse applications, but the problems of high latency and energy overhead are inevitable on resource-constrained devices. To address this challenge, most researchers focus on the…

Datalog-based languages are regaining popularity as a powerful abstraction for expressing recursive computations in domains such as program analysis and graph processing. However, existing systems often face a trade-off between efficiency…