Search Results for author: Shashikant Ilager

Found 12 papers, 4 papers with code

GREEN-CODE: Learning to Optimize Energy Efficiency in LLM-based Code Generation

1 code implementation19 Jan 2025 Shashikant Ilager, Lukas Florian Briem, Ivona Brandic

Results show that our method reduces the energy consumption between 23-50 % on average for code generation tasks without significantly affecting accuracy.

Bug fixing Code Completion +2

Investigating Energy Efficiency and Performance Trade-offs in LLM Inference Across Tasks and DVFS Settings

no code implementations14 Jan 2025 Paul Joe Maliakel, Shashikant Ilager, Ivona Brandic

To that end, in this work, we investigate the effect of important parameters on the performance and energy efficiency of LLMs during inference and examine their trade-offs.

Benchmarking Question Answering +1

DynaSplit: A Hardware-Software Co-Design Framework for Energy-Aware Inference on Edge

no code implementations31 Oct 2024 Daniel May, Alessandro Tundo, Shashikant Ilager, Ivona Brandic

While split computing enables the decomposition of large neural networks (NNs) and allows partial computation on both edge and cloud devices, identifying the most suitable split layer and hardware configurations is a non-trivial task.

Scheduling

ABBA-VSM: Time Series Classification using Symbolic Representation on the Edge

no code implementations14 Oct 2024 Meerzhan Kanatbekova, Shashikant Ilager, Ivona Brandic

Edge AI facilitates the processing of Internet of Things (IoT) data and provides privacy-enabled and latency-sensitive services to application users using Machine Learning (ML) algorithms, e. g., Time Series Classification (TSC).

Binary Classification Classification +2

A Decentralized and Self-Adaptive Approach for Monitoring Volatile Edge Environments

1 code implementation13 May 2024 Shashikant Ilager, Jakob Fahringer, Alessandro Tundo, Ivona Brandić

However, traditional monitoring systems have a centralized architecture for both data plane and control plane, which increases latency, creates a failure bottleneck, and faces challenges in providing quick and trustworthy data in volatile edge environments, especially where infrastructures are often built upon failure-prone, unsophisticated computing and network resources.

Edge-computing

FLIGAN: Enhancing Federated Learning with Incomplete Data using GAN

no code implementations25 Mar 2024 Paul Joe Maliakel, Shashikant Ilager, Ivona Brandic

Federated Learning (FL) provides a privacy-preserving mechanism for distributed training of machine learning models on networked devices (e. g., mobile devices, IoT edge nodes).

Federated Learning Privacy Preserving

SymED: Adaptive and Online Symbolic Representation of Data on the Edge

no code implementations6 Sep 2023 Daniel Hofstätter, Shashikant Ilager, Ivan Lujic, Ivona Brandic

Symbolic Representation (SR) algorithms are promising solutions to reduce the data size by converting actual raw data into symbols.

Anomaly Detection Data Compression +2

An Energy-Aware Approach to Design Self-Adaptive AI-based Applications on the Edge

1 code implementation31 Aug 2023 Alessandro Tundo, Marco Mobilio, Shashikant Ilager, Ivona Brandić, Ezio Bartocci, Leonardo Mariani

In this paper, we present an energy-aware approach for the design and deployment of self-adaptive AI-based applications that can balance application objectives (e. g., accuracy in object detection and frames processing rate) with energy consumption.

object-detection Object Detection +1

Energy and Thermal-aware Resource Management of Cloud Data Centres: A Taxonomy and Future Directions

no code implementations6 Jul 2021 Shashikant Ilager, Rajkumar Buyya

This paper investigates the existing resource management approaches in Cloud Data Centres for energy and thermal efficiency.

Management

Dynamic Scheduling for Stochastic Edge-Cloud Computing Environments using A3C learning and Residual Recurrent Neural Networks

1 code implementation1 Sep 2020 Shreshth Tuli, Shashikant Ilager, Kotagiri Ramamohanarao, Rajkumar Buyya

The ubiquitous adoption of Internet-of-Things (IoT) based applications has resulted in the emergence of the Fog computing paradigm, which allows seamlessly harnessing both mobile-edge and cloud resources.

Cloud Computing Scheduling

Artificial Intelligence (AI)-Centric Management of Resources in Modern Distributed Computing Systems

no code implementations9 Jun 2020 Shashikant Ilager, Rajeev Muralidhar, Rajkumar Buyya

Contemporary Distributed Computing Systems (DCS) such as Cloud Data Centres are large scale, complex, heterogeneous, and distributed across multiple networks and geographical boundaries.

Distributed Computing Management

Cannot find the paper you are looking for? You can Submit a new open access paper.