A preliminary roadmap for dependability research in fog computing

Abstract

Fog computing aims to support novel real-time applications by extending cloud resources to the network edge. This technology is highly heterogeneous and comprises a wide variety of devices interconnected through the so-called fog layer. Compared to traditional cloud infrastructure, fog presents more varied reliability challenges, due to its constrained resources and mobility of nodes. This paper summarizes current research efforts on fault tolerance and dependability in fog computing and identifies less investigated open problems, which constitute interesting research directions to make fogs more dependable.

A Survey on Trustworthiness for the Internet of Things

“…Regarding studies that present definitions on dependability and trustworthiness, some papers explore the state of the art and definitions [9], [42], [43], [56][57][58][59][60][61][62][63]. We also found surveys on trustworthiness [64][65][66][67][68] and dependability [69] and a systematic literature review (SLR) on dependability [70].…”

“…• Fault recovery or mitigation: A way of recovering from a failure in IoT is, for example, using load balancing between nodes to mitigate service discontinuation [74]. Some studies also deal with IoT fault recovery by using redundancy techniques [58]. • Fault prevention: When the system predicts a fault (perceive the fault condition before it occurs), the system can perform mechanisms to prevent a failure (which refers to the system's inability to operate).…”

“…Redundancy increases IoT systems' reliability and availability [58] by replicating data from one node to other nodes. When, for example, a fog node A fails, the system continues to operate if other fog nodes B and C have a data copy from the failed fog node A.…”

“…Availability ensures that the IoT system continues operating as long as possible. There are methods to keep the system available, like managing hardware redundancy [63], [82], and maintaining a fault management mechanism [58].…”

Enabling Fog-based Industrial Robotics Systems

“…Dependability approaches for fog computing in the literature are mainly proposed to address dependability requirements using fault management solutions and redundancy techniques [51]. Fault management solutions proposed are mainly considering threat detection tools like monitoring [52] for fault prevention and fault removal, or failure recovery solutions like reconfiguration upon failure [53].…”