Adaptive Configuration of Service-Based Smart Sensors in Edge Networks
ABSTARCT :
Edge computing promises to facilitate the collaboration of smart sensors at the network edge, in order to satisfying the delay constraints of certain requests, and decreasing the transmission of large-volume sensory data from the edge to the cloud. Generally, the functionalities provided by smart sensors are encapsulated as services, and the satisfaction of certain requests is reduced to the composition of services configured upon smart sensors in edge networks. Considering the dynamics and hard-to-prediction of incoming requests, an adaptive and online service configuration mechanism is essential, especially when various temporal constraints are prescribed by requests and satisfied by configured services. We formulate this problem in terms of a continuous time Markov decision process model based on the state-action-reward mechanism. A temporal-difference learning approach is developed to optimize service configuration, while taking long-term delay sensitivity and energy efficiency into consideration. Extensive experiments are conducted, and evaluation results show that our approach outperforms the state-of-art's techniques for achieving close-to-optimal service configuration, and improving temporal satisfaction of user requests.
EXISTING SYSTEM :
? Implementation depends on the design and existing technologies (hardware, communication, and software) that provide the required functionalities.
? This novel approach overcomes some drawbacks of existing designs related to interoperability and scalability of services.
? Pre-existing buildings, however, do not usually have these systems. Generally, each type of installation offers specific services: Heating Ventilation and Air Conditioning (HVAC) controls climate services, cameras and sensors offer security services, etc.
? Moreover, the potential of the services that can be offered also makes it attractive for pre-existing buildings.
DISADVANTAGE :
? In response to this problem, part of the network intelligence and data management should be distributed to gateways and routers in the interconnected systems creating fog and edge computing operations.
? Software and algorithms for distributed problem-solving and decision-making to various management parts of the IoT systems.
? However, due to the high frequency of 5.9 GHz for ITS-G5, the physical obstacles on the link path can be problematic for the signal propagation.
? Another problem of these methods and their modifications is that they are rather static in their operations.
PROPOSED SYSTEM :
• In this work, a method to design smart services based on the edge computing paradigm is analysed and proposed.
• It is an intensely researched topic where many works are being proposed; there are even review works that summarise cloud computing paradigm related studies.
• Reliable service provisioning methods are proposed to offer the system a higher resilience and provide agile and optimised cloud services.
• This protocol is proposed as communication paradigm between sensors, actuators, controllers, communication devices and subsystems.
• Machine learning models are proposed for different subsystems and can be installed on edge or fog nodes.
ADVANTAGE :
? These adaptive solutions are providing more stable network performance and optimizing the network path and resources.
? The system must be robust, providing high performance and scalable algorithms and protocols capable of handling varying number of devices, workload levels and heterogeneous networks.
? The latest development of scheduling methods is directed to the dynamic adaptation of scheduling parameters which gives better overall performance.
? REAC marking shows a very good performance, with a maximum utilization of approximately 97%.
? Computation offloading can overcome the resource and energy constraints on mobile devices requiring high performance computations to save storage and battery lifetime.
|