Research Interests
Concepts, paradigms, models, languages, algorithms, architectures, infrastructures, frameworks, protocols and formalisms for operating systems, distributed computations, scientific computing, high performance cluster computing, wireless sensor networks, wireless sensor actor networks, mobile computing, virtualization and cloud computing, peer-to-peer computing, autonomic computing, ubiquitous and pervasive computing, web engineering, and privacy & security concepts.
The ultimate research interest is to find the know-how and technology of engineering a truly distributed operating system — a kernelware — with embedded basic cells and primitives in support of all types of foreseen and unforeseen computations, running on heterogeneous platforms.
Research Areas
HPC · High Performance Computing
High Performance Computing is the study and realization of highest envisioned degrees of performability of applications. High performance issues are pertinent at six layers: applications, compilations, runtime supports, operating systems, networking, and hardware/micro-architecture.
Research topics
- Node-, socket-, CPU- and core-level scheduling of processes and virtual CPUs/cores
- Virtualization-aware/unaware job and task scheduling
- Cooperative, coordinated gang scheduling of jobs, tasks, VMs, and enclaves
- Communication-aware co-location and organization
- Energy-aware scheduling
- High-performance I/O, network, and memory management
- Topology-aware application-level and VM-level overlays
- Distributed computational and programming models for new HPC applications
HDA · High-performance Data Analytics
High-performance Data Analytics studies the system-level techniques that make data-intensive computations fast and scalable — from in-memory query execution to analytics on heterogeneous hardware.
Research topics
- In-memory and cache-aware analytics engines
- Query optimization for multicore and accelerator hardware
- Data-parallel computational models for big data
- Memory-aware data placement and partitioning
- Analytics on graphics and tensor accelerators
- Fast big data processing pipelines
ESC · Exa-Scale Computing
Exa-Scale Computing is the current mainstream of HPC research at the DSL. Key idea: breaking down HPC applications into standalone, scalable, possibly heterogeneous components running within an Enclave . Virtualization is the core enabling technology.
Research topics
- Enclave-wide and global scheduling of VMs to physical machines
- Runtime system software for general dynamic reconfiguration
- Distributed management of heterogeneous compute resources
- Light-weight OS and VMM, co-kernels
- Overlay communication networks for exascale
- Fault tolerance and resilience at extreme scale
DAI · Distributed AI Computing
Distributed AI Computing is the study of system-level support for machine learning workloads spread across clusters, cloud regions, and edge devices — from training to serving.
Research topics
- Distributed training and gradient aggregation
- Low-latency inference serving systems
- Scheduling and resource management for ML workloads
- Model partitioning and pipelining across heterogeneous hardware
- Federated learning and privacy-preserving ML
- System support for large language models
DSP · Distributed Stream Processing
Distributed Stream Processing targets continuous, low-latency computation over unbounded data flows. State-of-the-art systems must reconcile high throughput, low latency, and elasticity on heterogeneous hardware.
Research topics
- Operator scheduling on heterogeneous clusters
- Elastic and traffic-aware scheduling for data streams
- Stateful stream processing and fault recovery
- Parallelization of stream aggregations and detection tasks
- Ant colony optimization and heuristic schedulers
- Benchmarking and workload characterization for stream engines
CEP · Complex Event Processing
Complex Event Processing (CEP) analyzes and controls complex series of interrelated events driving modern distributed message-based systems. Applies to fraud detection, stock trading, business process automation, intrusion detection, and network monitoring.
Research topics
- Highly scalable CEP for large-scale applications
- Adaptive load balancing and rule distribution
- Applying CEP to critical information systems
- Middleware for federated CEP systems
- Simulation tools and environments specific to CEP
EFCC · Edge–Fog–Cloud Continuum
Edge–Fog–Cloud Continuum studies the orchestration of computation and data across a continuous spectrum from edge devices to fog nodes to centralized cloud — balancing latency, energy, and cost.
Research topics
- Service placement across the fog-cloud continuum
- Energy-aware and latency-aware orchestration
- Containerized elasticity in continuum environments
- Green IoT and sustainable service placement
- Mobility-aware and geo-distributed scheduling
WSAN · Wireless Sensor Actor Networks
WSANs are distributed systems of sensor and actuator nodes interconnected over wireless links. Sensors gather information; actuators perform actions that change the environment. Real-time, reliable communication is often more important than power consumption alone.
Research topics
- Coordination in weakly connected WSANs
- QoS in CORBA Component Model implementations
- Autonomous detection and repair of actor failures
- Reputation-based fault map extraction
- Improved key management for WSNs
- Task allocation and energy-aware partitioning for real-time applications
SEC · Security
Security protects information and property from theft, corruption, or natural disaster while remaining accessible to intended users. The lab's work spans systems-level security, web security, and privacy in distributed environments.
Research topics
- Intrusion detection at the Virtual Machine Monitor level
- Anti-phishing techniques and detection
- Detecting and preventing control-flow tampering
- Securing XML, e-payment, and web applications
- Privacy in pervasive and mobile environments
- Secure distributed machine learning
Selected Research Topics
- Load Balancing Distributed Web Crawlers Based on Web Structure
- A Security Framework for Web-Based Java Applications
- New Techniques against Phishing Attacks
- Scam Detection and Authentication
- Detecting and Preventing Control Flow Tampering Attacks
- Leveraging SELinux for Mandatory Access Control in the JVM
- Intrusion Detection at the Virtual Machine Monitor Level
- Policy-Based Resource Management for Autonomic Computing
- Improving Survivability of High Availability Clusters
- Secure Covert Communication with Image Steganography
- Improved Key Management for Wireless Sensor Networks
- Extending X3D in Support of E-Commerce Requirements
- Securing Electronic Forms using Elliptic Curves
- Test-Driven, Platform-Independent Software Frameworks
- Information Hiding using Fractal-Based Coding
- Prototyped Stateful Intrusion Detection Systems
- VPN Vulnerable Access Points: Attacks and Counterattacks
- Safe and Transparent Certificate Status Information Dissemination
- Securing ICC-Based E-Payment Systems
- Securing XML Documents
- Tuple Routing for Continuous Queries in WSNs
- Fractal-Based Visualization of Clouds and Lightning (FractVRML)
- Distributed Reservation-Based Real-Time Resource Management
- Fractal-Based Visualization of Mountains and Rivers
- Non-Orthogonal Modeling of Quantum Key Distribution
- Application of Fractals to Virtual Reality
- Proactive Detection of DDoS Attacks using MCB Traffic Variables
- Search Engines Based on Robots
- Cryptography using Pseudo-Random Numbers
- Edge Detection Algorithms in Image Processing
- Securing Mobile Agents
- Domain Engineering Applied to Banking
- Air Traffic Control Domain Engineering with RAISE
- Prototypical E-Commerce Systems
- 5-Axis Post-Processor for Anvil5K
- Expert System Kernel for Budget Planning
- Learner System for Cephalometry using Genetic Algorithms
- Expert Database for Rijal Science
- Hardware Security Provisioning
- Hypermedia Development Environment for Persian
- Numerical Simulation of Tooth Movement
- Orthodontic Cephalometry Analyzer
- Expert Prescription Software