Composing Efficient Computational Models for Real-Time Processing on Next-Generation Edge-Computing Platforms

In the era of IoT and smart systems, an enormous amount of data will be generated from various IoT/smart devices in smart homes, smart cars, etc. Typically, this big data is collected and sent directly to the cloud infrastructure for processing, analyzing, and storing. However, traditional cloud infrastructure faces serious challenges when handling this massive amount of data, including insufficient bandwidth, high latency, unsatisfactory real-time response, high power consumption, and privacy protection issues. The edge-centric computing is emerging as a complementary solution to address the aforementioned issues of the cloud infrastructure. Furthermore, for many real-world IoT and smart systems, such as smart cars, real-time, in situ, and online data analysis and processing are crucial. With edge computing, data processing and analysis can be done closer to the source of the data (i.e., at the edge of the networks), which in turn enables real-time and in-situ data analytics and processing. As a result, edge computing will soon become the cornerstone of many IoT and smart applications. However, edge computing is still in its infancy; thus, requires novel models and techniques to support real-time and in-situ data processing and analysis. In this research work, we introduce novel and efficient computation models that are suitable for real-time processing and analysis on next-generation edge-computing platforms. Since most common edge-computing tasks are data analytics/mining, we focus on widely used data analytics techniques, including dimensionality reduction and classification techniques, specifically, principal component analysis (PCA) and support vectors machine (SVM), respectively. This is mainly because it is demonstrated that combination of PCA and SVM leads to high classification accuracy in many fields. In this paper, we introduce three different PCA+SVM models (i.e., Model 1, Model 2, and Model 3), for real-time processing and analysis (for online training and inference) on edge computing platforms. Model 1 and Model 2 are created utilizing the same SVM algorithm but with a different design/functional flows, whereas Model 3 is created with the same functional flow as Model 2 but utilizing a modified SVM algorithm. Our experimental results and analysis demonstrate that Model 3 utilizes dramatically lower number of iterations to produce the results, compared to that of other two models, while achieving acceptable performance results. Our results and analysis demonstrate that Model 3 is the most suitable computation model for real-time processing and analysis of edge computing platform.