International Journal on Science and Technology

E-ISSN: 2229-7677   •   Impact Factor: 9.88

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 16 Issue 2 April-June 2025 Submit your research before last 3 days of June to publish your research paper in the issue of April-June.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 16 Issue 2
April-June 2025

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

Hybrid AI-Edge Architectures for Mission-Critical Decision Systems

Author(s) Sai Kalyani Rachapalli
Country United States
Abstract The unprecedented spread of Artificial Intelligence (AI) and Edge Computing technologies has propelled the development of mission-critical decision systems across applications like defense, healthcare, industrial automation, and autonomous transport. Conventional cloud-based models, though mighty, tend to lag in addressing the strict latency, reliability, and security demands unique to mission-critical domains. As a result, hybrid AI-Edge architectures have become a crucial paradigm, marrying centralized computational smarts with decentralized, near-data processing capabilities. This hybrid framework attempts to draw on the cloud's scalability for training and world orchestration while taking advantage of the edge node's immediacy and contextual sense for real-time decision making.
In a hybrid AI-Edge architecture, life-critical decisions are either taken completely at the edge or in coordination with cloud elements based on operational needs, system conditions, and communication availability. This flexibility provides uninterrupted operation even under hostile environments like network outages, cyber-attacks, or high-mobility environments. Methods like federated learning, edge model distillation, split computing, and light-weight neural architecture search (NAS) are being increasingly used to facilitate complex AI models on resource-limited edge devices. Additionally, secure multiparty computation and homomorphic encryption progress support data security and privacy in hybrid configurations, rendering them increasingly applicable to mission-critical applications with sensitive information.
Recent studies, including those by Zhang et al. (2023) and Kumar et al. (2022), prove that hybrid AI-Edge systems can realize major inference latency reductions (up to 60%) while also boosting operational resilience by 40% relative to solely cloud-based systems. New methodologies are also concerned with dynamic model partitioning, in which parts of a neural network are dynamically deployed on the cloud and edge according to system loading, bandwidth levels, and urgency of tasks. This smart partitioning guarantees preservation of key functions even in worst-case network environments.
The promise of hybrid architectures is further amplified when combined with emerging network technologies like 5G and 6G, which offer ultra-low latency, high throughput, and edge-native network functions. Edge orchestration platforms, leveraging containerization technology such as Kubernetes on Edge (KubeEdge) and light-weighted virtual machines, are being used to orchestrate dynamic scale, resource management, and model updates in real-time.
Nonetheless, substantial challenges remain. Model consistency-related issues, real-time synchronization, distributed failure recovery, AI model explainability in the edge, and resource heterogeneity require thorough solutions. Moreover, regulatory compliance (e.g., HIPAA for healthcare applications or GDPR for data privacy) adds complexity to hybrid deployments, requiring strong governance and monitoring structures.
This work gives an extensive review of hybrid AI-Edge architectures designed for mission-critical decision-making systems. We discuss state-of-the-art solutions systematically, outline an overall methodology for hybrid system development, show simulation and experimental results of a set of case studies, and outline further research directions to bridge current gaps. Through reconciliation of cloud wisdom and edge urgency, hybrid architectures mark a critical transition towards realizing scalable, robust, and intelligent mission-critical systems suitable for ever-increasing operational complexities.
Field Engineering
Published In Volume 14, Issue 4, October-December 2023
Published On 2023-12-07
DOI https://doi.org/10.71097/IJSAT.v14.i4.5505
Short DOI https://doi.org/g9mvvs
View / Download PDF File

Share this


CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 15 Isu 4Cover Page Vol 15 Isu 3Cover Page Vol 15 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJSAT
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us Message on WhatsApp +91-9687-182-185 editor@ijsat.org