Edge artificial intelligence (AI) is an innovative computing paradigm that aims to shift the training and inference of machine learning models to the edge of the network. This paradigm offers the opportunity to significantly impact our everyday lives with new services such as autonomous driving and ubiquitous personalized health care. Nevertheless, bringing intelligence to the edge involves several major challenges, which include the need to constrain model architecture designs, the secure distribution and execution of the trained models, and the substantial network load required to distribute the models and data collected for training. In this article, we highlight key aspects in the development of edge AI in the past and connect them to current challenges. This article aims to identify research opportunities for edge AI, relevant to bring together the research in the fields of artificial intelligence and edge computing.

The edge computing system attracts much more attention and is expected to satisfy ultra-low response time required by emerging IoT applications. Nevertheless, as there were problems on latency such as the emerging traffic requiring very sensitive delay, a new Edge Computing system architecture, namely Home Edge Computing (HEC) supporting these real-time applications has been proposed. HEC is a three-layer architecture made up of HEC servers, which are very close to users, Multi-access Edge Computing (MEC) servers and the central cloud. This paper proposes a solution to solve the problems of latency on HEC servers caused by their limited resources. The increase in the traffic rate creates a long queue on these servers, i.e., a raise in the processing time (delay) for requests. By leveraging, based on clustering and load balancing techniques, we propose a new technique called HEC-Clustering Balance. It allows us to distribute the requests hierarchically on the HEC clusters and another focus of the architecture to avoid congestion on a HEC server to reduce the latency. The results show that HEC-Clustering Balance is more efficient than baseline clustering and load balancing techniques. Thus, compared to the HEC architecture, we reduce the processing time on the HEC servers to 19% and 73% respectively on two experimental scenarios.

SDN has evolved to revolutionize next-generation networks, offering programmability for on-the-fly service provisioning, primarily supported by the OpenFlow (OF) protocol. The limited storage capacity of Ternary Content Addressable Memory (TCAM) for storing flow tables in OF switches introduces vulnerabilities, notably the Low-Rate Flow Table Overflow (LOFT) attacks. LOFT exploits the flow table’s storage capacity by occupying a substantial amount of space with malicious flow, leading to a gradual degradation in the flow-forwarding performance of OF switches. To mitigate this threat, we propose FloRa, a machine learning-based solution designed for monitoring and detecting LOFT attacks in SDN. FloRa continuously examines and determines the status of the flow table by closely examining the features of the flow table entries. When suspicious activity is identified, FloRa promptly activates the machine-learning based detection module. The module monitors flow properties, identifies malicious flows, and blacklists them, facilitating their eviction from the flow table. Incorporating novel features such as Packet Arrival Frequency, Content Relevance Score, and Possible Spoofed IP along with Cat Boost employed as the attack detection method. The proposed method reduces CPU overhead, memory overhead, and classification latency significantly and achieves a detection accuracy of 99.49% which is more than the state-of-the-art methods to the best of our knowledge. This approach not only protects the integrity of the flow tables but also guarantees the uninterrupted flow of legitimate traffic. Experimental results indicate the effectiveness of FloRa in LOFT attack detection, ensuring uninterrupted data forwarding and continuous availability of flow table resources in SDN.

The inherent characteristics of cloud systems often lead to anomalies, which pose challenges for high availability, reliability, and high performance. Detecting anomalies in cloud key performance indicators (KPI) is a critical step towards building a secure and trustworthy system with early mitigation features. This work is motivated by (i) the efficacy of recent reconstruction-based anomaly detection (AD), (ii) the misrepresentation of the accuracy of time series anomaly detection because point-based Precision and Recall are used to evaluate the efficacy for range-based anomalies, and (iii) detects performance and security anomalies when distributions shift and overlaps. In this paper, we propose a novel semi-supervised dynamic density-based detection rule that uses the reconstruction error vectors in order to detect anomalies. We use long short-term memory networks based on encoder-decoder (LSTM-ED) architecture to reconstruct the normal KPI time series. We experiment with both testbed and a diverse set of real-world datasets. The experimental results show that the dynamic density approach exhibits better performance compared to other detection rules using both standard and range-based evaluation metrics. We also compare the performance of our approach with state-of-the-art methods, outperforms in detecting both performance and security anomalies.