Intelligent edge machine learning has emerged as a paradigm for deploying smart applications across resource-constrained devices in next-generation network infrastructures. This survey addresses the critical challenges of implementing machine learning models on edge devices within distributed network environments, including computational limitations, memory constraints, and energy-efficiency requirements for real-time intelligent inference. We provide comprehensive analysis of soft computing optimization strategies essential for intelligent edge deployment, systematically examining model compression techniques including pruning, quantization methods, knowledge distillation, and low-rank decomposition approaches. The survey explores intelligent MLOps frameworks tailored for network edge environments, addressing continuous model adaptation, monitoring under data drift, and federated learning for distributed intelligence while preserving privacy in next-generation networks. Our work covers practical applications across intelligent smart agriculture, energy management, healthcare, and industrial monitoring within network infrastructures, highlighting domain-specific challenges and emerging solutions. We analyze specialized hardware architectures, cloud offloading strategies, and distributed learning approaches that enable intelligent edge computing in heterogeneous network environments. The survey identifies critical research gaps in multimodal model deployment, streaming learning under concept drift, and integration of soft computing techniques with intelligent edge orchestration frameworks for network applications. These gaps directly manifest as open challenges in balancing computational efficiency with model robustness due to limited multimodal optimization techniques, developing sustainable intelligent edge AI systems arising from inadequate streaming learning adaptation, and creating adaptive network applications for dynamic environments resulting from insufficient soft computing integration. This comprehensive roadmap synthesizes current intelligent edge machine learning solutions with emerging soft computing approaches, providing researchers and practitioners with insights for developing next-generation intelligent edge computing systems that leverage machine learning capabilities in distributed network infrastructures.

The rise of edge computing has enabled diverse IoT applications while introducing new challenges in latency, resource constraints, and continuous model adaptations across the IoT–Edge–Cloud continuum. Addressing these issues requires optimizing the trade-off between efficiency and latency on resource-constrained hardware, fostering collaboration, and advancing model compression and green computing to reduce computational overhead. We introduce OASIS, an open source library-agnostic framework for scalable Edge Machine Learning that unifies predictive analytics, model compression, and supports FL for privacy-preserving training in distributed environments. Designed for real-time forecasting and adaptive monitoring, OASIS enables lightweight ML deployments in dynamic settings with limited resources. OASIS simplifies adoption by offering modular APIs and pre-integrated tools, allowing users to plug in models or connect telemetry data with minimal configuration, making it suitable for practitioners across domains. Our implementation integrates drift detection, SHAP-based explainability, and end-to-end MLOps and monitoring via MLFlow and NannyML.We have presented illustrative examples using real and synthetic data, particularly synthetic CPU telemetry, to stress-test the robustness of the system and demonstrate improvements in inference speed, memory efficiency, and fault resilience. By consolidating critical AI capabilities into a single interface, OASIS lowers the barrier for deploying robust, adaptive, and FL applications at the edge. The code is publicly available here: https://github.com/icos-project/intelligence-module.

The increasing demand for artificial intelligence (AI) workloads across diverse computing environments has driven the need for more efficient data management strategies. Traditional cloud-based architectures struggle to handle the sheer volume and velocity of AI-driven data, leading to inefficiencies in storage, computation, and data movement. This paper explores the integration of active storage systems within the computing continuum to optimize AI workload distribution. By embedding computation directly into storage architectures, active storage is able to reduce data transfer overhead, enhancing performance and improving resource utilization. Other existing frameworks and architectures offer mechanisms to distribute certain AI processes across distributed environments; however, they lack the flexibility and adaptability that the continuum requires, both regarding the heterogeneity of devices and the rapid-changing algorithms and models being used by domain experts and researchers. This article proposes a software architecture aimed at seamlessly distributing AI workloads across the computing continuum, and presents its implementation using mainstream Python libraries and dataClay, an active storage platform. The evaluation shows the benefits and trade-offs regarding memory consumption, storage requirements, training times, and execution efficiency across different devices. Experimental results demonstrate that the process of offloading workloads through active storage significantly improves memory efficiency and training speeds while maintaining accuracy. Our findings highlight the potential of active storage to revolutionize AI workload management, making distributed AI deployments more scalable and resource-efficient with a very low entry barrier for domain experts and application developers.