ﺗﺨﻠﯿﻪﺑﺎر ﻣﺤﺎﺳﺒﺎﺗﯽ ﺗﺤﺮکآﮔﺎه ﻣﺒﺘﻨﯽ ﺑﺮ ﭘﯿﺶﺑﯿﻨﯽ در راﯾﺎﻧﺶ ﻟﺒﻪ ﺑﺎ دﺳﺘﺮﺳﯽ ﭼﻨﺪﮔﺎﻧﻪ

اﻣﺮوزه ﺑﺎ ﭘﯿﺎدهﺳﺎزی ﻧﺴﻞ ﺟﺪﯾﺪ ﺷﺒﮑﻪﻫﺎی ارﺗﺒﺎﻃﯽ، ﺷﺎﻫﺪ ﺗﺤﻮﻟﯽ ﻋﻈﯿﻢ در ﺗﻮﺳﻌﻪ اﯾﻨﺘﺮﻧﺖ اﺷﯿﺎء و ﻇﻬﻮر ﺑﺮﻧﺎﻣﻪﻫﺎی ﺟﺪﯾﺪ در اﯾﻦ ﺑﺴﺘﺮ ﻣﯽﺑﺎﺷﯿﻢ. ﻣﺤﺪودﯾﺖ در ﺗﻮان ﻣﺤﺎﺳﺒﺎﺗﯽ و اﻧﺮژی دﺳﺘﮕﺎهﻫﺎی ﻣﺘﺼﻞ ﺑﻪ اﯾﻦ ﺑﺴﺘﺮ ﻣﻮﺟﺐ اﯾﺠﺎد ﭼﺎﻟﺶ و ﻋﺪم ﭘﺸﺘﯿﺒﺎﻧﯽ اﯾﻦ دﺳﺘﮕﺎهﻫﺎ ﺑﺮای اﺟﺮای ﺑﺮﻧﺎﻣﻪﻫﺎ ﺑﺎ ﺑﺎر ﻣﺤﺎﺳﺒﺎﺗﯽ ﺑﺎﻻ و ﻧﯿﺎزﻣﻨﺪ ﺗﺎﺧﯿﺮ ﮐﻢ ﻣﯽﺷﻮد. روشﻫﺎی ﺗﺨﻠﯿﻪﺑﺎر ﻣﺤﺎﺳﺒﺎﺗﯽ در راﯾﺎﻧﺶ ﻟﺒﻪ ﺑﺎ دﺳﺘﺮﺳﯽ ﭼﻨﺪﮔﺎﻧﻪ، ﺑﺎ ﻓﺮاﻫﻢ آوردن ﻣﻨﺎﺑﻊ ﻣﺤﺎﺳﺒﺎﺗﯽ و ذﺧﯿﺮهﺳﺎزی در ﻧﺰدﯾﮑﯽ ﮐﺎرﺑﺮ راﻫﮑﺎری ﮐﺎرآﻣﺪ ﺑﺮای ﻣﻘﺎﺑﻠﻪ ﺑﺎ ﭼﺎﻟﺶﻫﺎی ذﮐﺮ ﺷﺪه اﺳﺖ. ﺑﺎ اﯾﻦ وﺟﻮد، ﺑﻪ ﻋﻠﺖ ﺗﺤﺮک ﮐﺎرﺑﺮ و ﺗﻐﯿﯿﺮ در ﻣﺸﺨﺼﺎت ﺑﺮﻧﺎﻣﻪﻫﺎی ﺗﺨﻠﯿﻪﺷﺪه در ﻃﻮل زﻣﺎن، ﻣﺴﺌﻠﻪ ﺗﺨﺼﯿﺺ ﺧﺪﻣﺖﮔﺰاران ﻟﺒﻪ ﺑﻪ ﮐﺎرﺑﺮان ﺑﺎ ﻫﺪف ﮐﺎﻫﺶ ﺗﺎﺧﯿﺮ ﺑﺎ ﭼﺎﻟﺶﻫﺎﯾﯽ ﻣﻮاﺟﻪ اﺳﺖ. روﯾﮑﺮدﻫﺎی ﻓﻌﻠﯽ ﺗﺨﻠﯿﻪﺑﺎر ﺗﺤﺮکآﮔﺎه در اﯾﻦ ﺣﻮزه از ﻣﺪلﻫﺎی ﺗﺤﺮک ﺗﺼﺎدﻓﯽ و ﻏﯿﺮواﻗﻊ-ﮔﺮاﯾﺎﻧﻪای اﺳﺘﻔﺎده ﻣﯽﮐﻨﻨﺪ و ﻫﻤﭽﻨﯿﻦ اﺟﺮای ﺗﺨﻠﯿﻪﺑﺎر در آنﻫﺎ ﺑﻪ ﺻﻮرت درﺷﺖداﻧﻪ ﺻﻮرت ﻣﯽﮔﯿﺮد. در اﯾﻦ ﻣﻘﺎﻟﻪ ﺗﺨﻠﯿﻪﺑﺎر ﺑﻪ ﻣﻨﻈﻮر ﺑﻬﺮهﻣﻨﺪی از ﻣﺰاﯾﺎی آن رﯾﺰداﻧﻪ ﻣﯽﺑﺎﺷﺪ. ﺑﺮ اﯾﻦ اﺳﺎس ﺑﺮﻧﺎﻣﻪ ﮐﺎرﺑﺮان ﺑﻪ ﺗﻌﺪادی ﻣﻮﻟﻔﻪ ﺗﻘﺴﯿﻢ و اﺧﺬ ﺗﺼﻤﯿﻢ ﺗﺨﻠﯿﻪ ﺑﺎ ﺗﻮﺟﻪ ﺑﻪ ﺗﺤﺮک و ﻣﺸﺨﺼﺎت ﻣﻮﻟﻔﻪﻫﺎی ﮐﺎرﺑﺮان در ﻃﻮل ﺷﮑﺎفﻫﺎی زﻣﺎﻧﯽ ﺗﻌﺮﯾﻒ ﺷﺪه در ﺳﯿﺴﺘﻢ، اﻧﺠﺎم ﻣﯽﮔﯿﺮد. اﯾﻦ ﺗﺼﻤﯿﻢ ﻋﻼوه ﺑﺮ ﺑﻬﯿﻨﻪ ﺑﻮدن در ﻣﻮرد ﻫﺮ ﻣﻮﻟﻔﻪ ﺑﻪ ﮐﺎﻫﺶ ﺳﺮﺑﺎر ﻧﺎﺷﯽ از ﻣﻬﺎﺟﺮت ﯾﮏ ﻣﻮﻟﻔﻪ ﺑﻪ ﻧﺴﺒﺖ ﮐﻞ ﺑﺮﻧﺎﻣﻪ ﻧﯿﺰ ﻣﻨﺠﺮ ﻣﯽﺷﻮد. ﻫﻤﭽﻨﯿﻦ، ﺑﻪ ﻣﻨﻈﻮر اﺧﺬ ﺗﺼﻤﯿﻢ ﺑﻬﯿﻨﻪ در راﺳﺘﺎی ﻧﯿﻞ ﺑﻪ ﻫﺪف ﻣﺴﺌﻠﻪ ﯾﻌﻨﯽ ﮐﻤﯿﻨﻪ ﮐﺮدن ﺑﺮآﯾﻨﺪ زﻣﺎن ﺗﺨﻠﯿﻪﺑﺎر، از ﭘﯿﺶﺑﯿﻨﯽ ﻣﺸﺨﺼﺎت ﮐﺎرﺑﺮان و ﻣﻮﻗﻌﯿﺖ ﻣﮑﺎﻧﯽ آنﻫﺎ اﺳﺘﻔﺎده ﻣﯽﮐﻨﯿﻢ. ﺑﺎ ﺗﻮﺟﻪ ﺑﻪ ﻧﺘﺎﯾﺞ ﺑﻪ دﺳﺖآﻣﺪه از ارزﯾﺎﺑﯽ، ﻣﺸﺎﻫﺪه ﻣﯽﺷﻮد ﮐﻪ روش ﭘﯿﺸﻨﻬﺎدی ﺑﻪ ﻧﺴﺒﺖ روشﻫﺎی ﻣﻮرد ﻣﻘﺎﯾﺴﻪ دارای ﺑﻬﺒﻮد در ﺗﺎﺑﻊ ﻫﺪف ﻣﺴﺌﻠﻪ و ﭘﯿﭽﯿﺪﮔﯽ ﻣﺤﺎﺳﺒﺎﺗﯽ اﺧﺬ ﺗﺼﻤﯿﻢ اﺳﺖ.

prediction-based mobility-aware computation offloading in multi-access edge computing

today, as the new generation of communication networks is implemented, we are witnessing a considerable change in iot development and new programs in this context. despite recent advancements in mobile networks and devices, the limitations of devices connected to this platform in terms of computational power and energy have resulted in sever challenges for running resource-intensive programs with exigent latency requirements. to address these challenges, the concept of computation offloading in multi-access edge computing mec has been recently developed, in which storage and computation resources are provided close to the user. however, due to the user mobility and changes in the profile of offloaded applications over time, the problem of assignment of edge servers to users with the aim of minimizing the overall offloading latency is a complicated task. in this regard, existing mobility-aware offloading approaches are not based on fine-grain offloading and use random and unrealistic mobility models. in this article, to address the aforementioned challenges, we propose a mobility-aware fine-grain computation offloading method to minimize the overall offloading delay. in the proposed approach, the user application is divided into several components and the offloading decision is made for each component according to the mobility and specifications of user components during the time slots defined in the system. in oner hand, this latter results in more efficient offloading decision. in the other hand, it reduces the overhead of migration since the migration of a subset of program’s components imposes lower cost compared to the migration of the entire program. moreover, we use user profile and location prediction to optimize the offloading decisions considering the underlying context over time. according to the evaluation results, it is observed that the proposed method achieves significantly better performance compared to other alternatives while the complexity of offloading decision is kept very low.