Computation Offloading Approaches In Mobile Edge-cloud Computing

Today,the Internet of Things(Io T)network technology is fully embraced by virtually every aspect of our lives.In addition,advances in mobile Io T devices,sensors,and communication technologies lead to the proliferation of complex,delay-and computationintensive Io T applications that often generate and process large volumes of data.However,mobile Io T devices’ limited battery capacity further restricts the execution of such resource-demanding applications on the devices.To alleviate these limitations and meet the communication/processing delay requirement,complex computations can be offloaded to more resourceful devices.Mobile cloud and edge computing paradigms are considered viable and promising solutions to provide flexible processing,storage,and services capabilities while reducing battery consumption.However,offloading the data over a wireless channel can increase the system’s vulnerability to different types of attacks.Consequently,allocating the radio resources efficiently,selecting the appropriate parameters for determining the offloading decision,caching the computation tasks at edge servers,and balancing the load among different base stations have played a critical role in the computation offloading model’s success.This thesis mainly addresses resource allocation,security,compression,task caching,and load balancing related issues by proposing efficient and secured computation offloading approaches for edge-cloud computing systems.Moreover,this study examines the techniques with a significant influence on system consumption cost.The key contributions of this thesis are summarized as follows:First,a novel and secure framework is proposed to offload intensive computation tasks dynamically through an integer problem formulation based on memory usage,CPU utilization,energy consumption,and execution time.In addition,a new security layer of AES technique is introduced to protect the transmitted data.Moreover,three different types of mobile applications are utilized to examine framework’s efficiency in selecting the proper offloading decision.Second,an efficient and secure multi-user multi-task computation offloading model is presented with guaranteed performance in latency,energy,and security for mobile-edge computing.This model does not only investigate offloading strategy but also considers resource allocation,compression,and security issues.Firstly,to guarantee efficient utilization of the shared resource in multi-user scenarios,radio,and computation resources are jointly addressed.In addition,JPEG and MPEG4 compression algorithms are used to reduce the transfer overhead.To fulfill security requirements,a security layer is introduced to protect the transmitted data from cyber-attacks.Third,task caching and computation offloading are jointly modeled for multi-user,multi-task MEC,in which the application code and related library for the completed tasks are cached at the edge server to reduce the delay and energy overhead.Then,an equivalent form of reinforcement learning is created where the state spaces are defined based on all possible solutions and the actions are defined based on movement between the different states.Afterward,two efficient Q-Learning and Deep-Q-Network-based algorithms have been proposed to derive the near-optimal decision for this problem.Fourth,our study is extended by considering a multi-tier edge-cloud computing environment.In this study,in addition to proposing a joint load balancing and computation offloading technique for edge-cloud computing systems,a new security layer is introduced to circumvent potential security issues.First,a load balancing algorithm for the efficient redistribution of Io T devices among base stations is proposed.In addition,a new advanced encryption standard(AES)cryptographic technique suffused with electrocardiogram(ECG)signal-based encryption and decryption key is presented as a security layer to safeguard the vulnerability of data during the transmission.Finally,this thesis conducts the test experiments on different scenarios and approaches.Detailed simulation results show that the proposed model with and without the additional security layers saves system consumption and obtains better performance than other benchmark solutions.