Mobile edge computing (MEC) paves the way to alleviate the burden of energy and computation of mobile users (MUs) by offloading tasks to the network edge. To enhance the MEC server utilization by optimizing its resource allocation, a well-designed pricing strategy is indispensable. In this paper, we consider the edge offloading scenario with energy harvesting devices, and propose a dynamic differential pricing system (DDPS), which determines the price per unit time according to the usage of computing resources to improve the edge server utilization. Firstly, we propose an offloading decision algorithm to decide whether to conduct the offloading operation and how much data to be offloaded if conducted, the algorithm determines offloading operation by balancing the energy harvested with the energy consumed. Secondly, for the offloading case, we formulate the game between the MUs and the server as a Stackelberg game, and propose a differential pricing algorithm to determine the optimal computing resources required by MUs. Furthermore, the proposed algorithm also reallocates computing resources for delay-sensitive devices while server resources are surplus after the initial allocation, aiming to make full use of the server computing resources. Extensive simulations are conducted to demonstrate the effectiveness of the proposed DDPS scheme.

翻译：移动边缘计算通过将任务卸载至网络边缘，为减轻移动用户在能量与计算方面的负担开辟了可行途径。为通过优化资源分配提升边缘服务器利用率，设计合理的定价策略至关重要。本文针对配备能量采集设备的边缘卸载场景，提出了一种动态差制定价系统，该系统根据计算资源使用情况确定单位时间价格，以提高边缘服务器利用率。首先，我们提出一种卸载决策算法，用于决定是否执行卸载操作以及卸载时的数据量，该算法通过平衡采集能量与消耗能量来确定卸载方案。其次，针对卸载情况，将移动用户与服务器之间的博弈建模为Stackelberg博弈，并提出一种差制定价算法来确定移动用户所需的最优计算资源。此外，该算法在初始分配后服务器资源仍有剩余时，为时延敏感型设备重新分配计算资源，旨在充分利用服务器计算资源。通过大量仿真实验验证了所提出的DDPS方案的有效性。