تخصیص منابع محاسباتی در محاسبات مه اینترنت اشیا با استفاده از الگوریتم بهینه سازی مبتنی بر آموزش - یادگیری

از آﻧﺠﺎ ﮐﻪ اﯾﻨﺘﺮﻧﺖ اﺷﯿﺎ ﺑﺎ ﺣﺠﻢ زﯾﺎدی از داده ﺳﺮوﮐﺎر دارد، ﭘﺮدازش و ذﺧﯿﺮه اﯾﻦ ﺣﺠﻢ از داده ﺑﻪ راﺣﺘﯽ اﻣﮑﺎن ﭘﺬﯾﺮ ﻧﯿﺴﺖ. ﺑﺎ اﯾﻦ ﺣﺎل، ﺑﺴﯿﺎری از ﺑﺮﻧﺎﻣﻪﻫﺎی آن از ﭼﺎﻟﺶﻫﺎی ﻣﺤﺎﺳﺒﺎت اﺑﺮی ﻣﺎﻧﻨﺪ ﺗﺄﺧﯿﺮ، آﮔﺎﻫﯽ از ﻣﮑﺎن و ﭘ ﺸﺘﯿﺒﺎﻧﯽ از ﺗﺤﺮک در زﻣﺎن واﻗﻌﯽ رﻧﺞ ﻣﯽﺑﺮﻧﺪ. ﻣﺤﺎ ﺳﺒﺎت ﻣﻪ، ﺑﻪ اراﺋﻪ راهﺣﻞﻫﺎﯾﯽ ﺑﺮای اﯾﻦ ﭼﺎﻟﺶﻫﺎ ﮐﻤﮏ ﻣﯽﮐﻨﺪ. در اﯾﻦ ﻣﻘﺎﻟﻪ اﺑﺘﺪا ﻣﺴﺄﻟﻪ آن ﮐﻪ از ﻧﻮع minlp ا ﺳﺖ ﺑﺎ اﺳﺘﻔﺎده از روشﻫﺎی pso ،sa + ga ،tlbo و ga ﺣﻞ ﻣﯽﺷﻮد. ﺳﭙﺲ ﺑﺎ ﺗﻮﺟﻪ ﺑﻪ ﻧﺘﺎﯾﺞ ﺣﺎﺻﻞ از آن، روش tlbo را ﮐﻪ ﺑﻬﺘﺮﯾﻦ ﻧﺘﺎﯾﺞ را در ﺑﯿﻦ ﭼﻬﺎر روش دارد اﻧﺘﺨﺎب ﮐﺮدﯾﻢ. اﯾﻦ ﻣﻘﺎﻟﻪ، ﺷﺎﻣﻞ ﯾﮏ ﺷﺒﯿﻪ ﺳﺎزی ﺷﺒﮑﻪ اﯾﻨﺘﺮﻧﺖ ا ﺷﯿﺎ ﺑﺮای ﺗﺨﺼﯿﺺ ﻣﻨﺎﺑﻊ ا ﺷﺘﺮاﮐﯽ ﺑﻬﯿﻨﻪ درﻣﺤﺎ ﺳﺒﺎت ﻣﻪ ا ﺳﺖ ﮐﻪ ﻫﺪف آن ﺑﯿﺸﯿﻨﻪ ﮐﺮدن ﺳﻮد اراﺋﻪدﻫﻨﺪﮔﺎن ﺧﺪﻣﺎت اﺑﺮی از ﻃﺮﯾﻖ ﻣﺤﺎ ﺳﺒﺎت ﻣﻪ ا ﺳﺖ. ﻣﻌﻤﺎری ﺷﺒﮑﻪ، ﺷﺎﻣﻞ ﺳﻪ ﻻﯾﻪ اراﺋﻪدﻫﻨﺪﮔﺎن ﺧﺪﻣﺎت اﺑﺮی، ﮔﺮهﻫﺎی ﻣﻪ و ﮐﺎرﺑﺮان ا ﺳﺖ. در اﯾﻦ ﻣﻘﺎﻟﻪ، ﺷﺒﮑﻪ ﺳﻪ ﻻﯾﻪاﯾﯽ ﺷﺒﯿﻪ ﺳﺎزی ﺷﺪه و اﻟﮕﻮرﯾﺘﻢ ﻣﻮرد ا ﺳﺘﻔﺎده در اﯾﻦ ﻣﺴﺄﻟﻪ، اﻟﮕﻮرﯾﺘﻢ ﺑﻬﯿﻨﻪ ﺳﺎزی ﻣﺒﺘﻨﯽ ﺑﺮ آﻣﻮزش - ﯾﺎدﮔﯿﺮی ﻣﯽﺑﺎ ﺷﺪ، ﮐﻪ ﺑﺎ ا ﺳﺘﻔﺎده از دو ﻓﺎز ﯾﺎدﮔﯿﺮی و آﻣﻮزش ﺑﻬﺘﺮﯾﻦ ﮔﺮه ﻣﻪ ﺑﺮای اراﯾﻪ ﺧﺪﻣﺎت ﺑﻪ ﮐﺎرﺑﺮ اﻧﺘﺨﺎب و ﺳﻪ ﭘﺎراﻣﺘﺮ درآﻣﺪ اراﺋﻪدﻫﻨﺪﮔﺎن اﺑﺮی، ﻣﯿﺎﻧﮕﯿﻦ ﺗﺎﺧﯿﺮ و ر ﺿﺎﯾﺖ ﮐﺎرﺑﺮان ﮐﻪ ﺑﺎ ﻫﺪف ﺗﺨ ﺼﯿﺺ ﻣﻨﺎﺑﻊ ﻣﺸﺘﺮک اﺳﺖ ﻣﺤﺎﺳﺒﻪ ﻣﯽﮔﺮدد. اﯾﻦ اﻟﮕﻮرﯾﺘﻢ ﺑﻪ روی ﻣﺪل اﺟﺮا ﺷﺪه و ﺑﺎ روش ﺗﺼﺎدﻓﯽ ﻣﻘﺎﯾﺴﻪ ﻣﯽ ﺷﻮد. اﯾﻦ ﻣﺪل و اﻟﮕﻮرﯾﺘﻢ ﻣﻨﺘﺨﺐ، ﻧﺴﺒﺖ ﺑﻪ اﻟﮕﻮرﯾﺘﻢﻫﺎی اﺳﺘﻔﺎده ﺷﺪه در ﺣﻞ ﻣﺪلﻫﺎی ﻣﺸﺎﺑﻪ اﯾﻦ ﻣ ﺴﺄﻟﻪ، ﺳﻮد اراﺋﻪدﻫﻨﺪﮔﺎن ﺧﺪﻣﺎت را اﻓﺰاﯾﺶ ﻣﯽدﻫﺪ.

Computational Resource Allocation in IoT Fog Computing using Teaching–Learning-Based Optimization Algorithm

Because the Internet of Things (IoT) deals with large amounts of data, it is not easy to process and store this amount of data. However, many of its applications suffer from cloud computing challenges such as latency, location awareness and realtime mobility support. Fog calculations help provide solutions to these challenges. This paper includes an IoT network simulation for allocating optimal shared resources in fog computing to solve the mix integer nonlinear programming (MINLP) problem, which aims to maximize the profitability of cloud service providers through fog computing. The network architecture consists of three layers: cloud service providers, fog nodes, and users. In this paper, the threelayer network is simulated and the algorithm used in this problem is the Teaching–LearningBased Optimization (TLBO) algorithm, which uses two phases of learning and teaching for the three parameters of cloud service providers’ revenue, average delay and user satisfaction for selecting the best node with the aim of allocating shared resources. This algorithm is implemented on the model and compared with a random method. This model and algorithm increases the profit of service providers compared to the algorithms used to solve similar models.