Collaborative caching strategy based on optimization of latency and energy consumption in MEC

Abstract

Mobile edge computing effectively reduces the network delay of requests during data transmission, reduces the transmission burden of data traffic in the network, and improves the quality of mobile services. However, the introduction of mobile edge computing architecture increases the cost of the actual network infrastructure deployment, which increases the complexity of resource management. An edge network architecture based on software-defined network technology is proposed, in which the SDN controller with the entire network state can manage data transmission more intelligently to maximize the utilization of edge servers. In addition, to solve the problems of high request delay and high operating cost in current caching strategies based on video services, a video caching strategy for mobile edge computing is proposed. First, we analyze the user’s request data and use the neural network model to predict the content of the user’s subsequent time slice request and pre-cache the user’s request. Then, improve the quality of user experience and choose the most appropriate edge node cache deployment plan. Finally, a video caching strategy for mobile edge computing with coordinated optimization of delay and energy consumption is proposed. The Branch and Bound algorithm is used to solve the optimization problem. Finally, we compared our algorithm with the LFU algorithm, PBC algorithm, COC algorithm, and R-LCCA algorithm. Experimental results show that the algorithm has a high cache hit rate, thereby reducing the cost of video providers and improving the quality of user experience.