مقاله انگلیسی رایگان در مورد محاسبات لبه در محیط صنعتی اینترنت اشیا – IEEE 2018

The need for on-demand state-of-the-art services (smart sensing, e-healthcare, smart transportation, etc.) and computing infrastructure has paved way to the powerful paradigm of cloud computing. Ever since its inception in 2000, the cloud computing paradigm has witnessed significant transitions in its overall usage, size, computational ability, and underlying technology [1]. This is evident from the widescale adoption of cloud computing infrastructure by the IT vendors. According to 451 Research, the cloud services would witness an overall increase in their worldwide market from $21.9 billion in 2016 to $44.2 billion by 2020 [2]. This tremendous popularity can be attributed to the cloud’s “pay-per-use” model, wherein users utilize the available resources of storage, computation, and networking as per their demands. The National Institute of Standards and Technology (NIST) has listed five essential attributes of cloud computing: • On-demand self-service • Broad network access • Resource pooling • Rapid elasticity • Measured service These attributes are typically achieved by the underlying service oriented architecture (SOA) that supports services as per the respective enterprise model, that is, everything-as-a-service (EaaS or XaaS). These enhanced flexibility and reliability attributes offered by the cloud computing platform have led to its widespread popularity among academia and industry. However, with the emergence of the Internet of Things (IoT), the need for realtime data storage, access, and processing at the cloud has grown manifold. Moreover, the big data generated by the connected devices (smartphones, PDAs, wireless body sensors, smart meters, etc.) would be on the order of zettabytes in the near future. This is evident as per the latest statistics shared by Gartner in its annual report [3]. It advocates that nearly 50 billion devices would be connected to the Internet by 2020. Hence, the relaying of such huge data to the cloud infrastructure may create network bottlenecks in the future. Additionally, this would lead to latency issues which in turn may affect the overall quality of service (QoS) for various applications in this environment.