DATA SCIENCE AND IOT MANAGEMENT SYSTEM

DATA SCIENCE AND IOT MANAGEMENT SYSTEM

Towards a Reference Architecture for Intelligent Anomaly Detection in Software-Defined Networks

Emerging technologies such as Cloud Computing, 5G, the Internet of Things (IoT), and Edge Computing demand the management of large-scale and highly dynamic network infrastructures. Traditional network configuration does not scale efficiently, whereas Software-Defined Networking (SDN) enables centralized control and simplified management. Despite these benefits, SDN environments still face significant challenges related to security and fine-grained anomaly detection. Several studies have demonstrated the effectiveness of computational intelligence (CI) techniques for anomaly detection in SDN. However, the diversity of network anomalies and CI-based solutions introduces substantial heterogeneity, making model selection and integration challenging. This paper proposes a reference architecture designed to validate, promote, and explain the suitability of different CI techniques for distinct network anomaly scenarios. The proposed architecture adopts a hexagonal microservices design and a unified information model aligned with the application, information, and process layers of the TM Forum Open Digital Architecture (ODA). Validation was performed through a proofof-concept prototype using two datasets and seven machine learning algorithms. The results demonstrate the importance of architectural flexibility, enabling the dynamic integration and replacement of CI models to support adaptive and scalable SDN anomaly detection.

Edge–Cloud Orchestration for IoT Services: Technologies, Architectures, and Research Directions

This review explores the recent approaches of the state of the art focused on service orchestration in IoT edge-cloud environments, concentrating on architectures and methodologies that enable resource allocation and service management.

ADIMS: A Multi-Protocol IoT and Sensor Network Platform for Sustainable Infrastructure Monitoring

This paper introduces ADIMS (Adaptive Distributed Infrastructure Monitoring System), a cloud-based telemetry platform that facilitates real-time monitoring and management of distributed field infrastructure across various organizational contexts. ADIMS solves the complex problem of integrating diverse devices by supporting multiple communication protocols, including TCP/IP, MODBUS, LoRaWAN, Sigfox, and LTE. This makes it easy to get data from third-party sensors and equipment. The system architecture has three main layers: a field acquisition layer that supports multi-protocol communication, a cloud-based processing and analytics engine, and a customizable dashboard framework that gives operational and managerial insights. We show that ADIMS could be used in smart city infrastructure by looking at similar systems and finding that they could use 15–30% less energy and save 25–35% on predictive maintenance costs. The platform’s protocol-agnostic design makes it easy to set up quickly at universities, NGOs, government buildings, and industrial sites. This helps achieve sustainable resource management and climate action goals that align with the UN Sustainable Development Goals.

An Adaptive Multi-Protocol IoT Gateway for Resilient Edge-Cloud Communication: An ns-3-Based Evaluation

An adaptive edge gateway for ZigBee-based IoT networks that can switch between MQTT and CoAP as needed, and shows that adaptive switching improves packet delivery by 15–20% during faults in comparison to static setups and reduces recovery time without much extra overhead.

Edge–Cloud Intelligence in Disaster Management: A Review of Architectures, Challenges, and Opportunities

Natural disasters are happening more often and with more force, which puts a lot of stress on disaster management systems. They require fast, reliable and sustainable technologies. In conventional centralized systems, there are problems with latency, network congestion and a requirement for continuous connectivity. These can slow down the early detection and rapid response. In this study, the Smart Disaster Alert Response System (SDARS), a new approach that integrates cloud computing, edge computing, and green computing to enhance resilience, cut down latency and ensure sustainability. SDARS relies on IoT sensors that constantly monitor the environment, and edge nodes that do initial data processing to provide real-time alerts with low latency. The cloud allows for big data analysis to be conducted to gain predictive knowledge and optimise resource allocation. Energy-efficient (green computing) techniques are also used to conserve energy and extend the lifespan of devices in low-energy environments. The experimental evaluation of SDARS reveals that it can raise alarms in less than a second, consumes 35% less energy compared to conventional systems and continues to operate despite network partition. In conclusion, the proposed model demonstrates how distributed computing techniques with energy-aware techniques can result in scalable and sustainable disaster response systems.