Edge cache scheduling and task unloading method and system oriented to heterogeneous task generalization

• Main Authors: WEI ZHENCHUN, FAN YUQI, SHI LEI, LV ZENGWEI, ZHANG BENHONG, ZHAO YANG
• Format: Patent
• Language: Chinese; English
• Published: 15.11.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRIC DIGITAL DATA PROCESSING; ELECTRICITY; PHYSICS; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

The invention provides an edge cache scheduling and task unloading method and system oriented to heterogeneous task generalization. The invention discloses a heterogeneous task generalization-oriented edge cache scheduling method, which comprises the following steps of: firstly, training a basic model by adopting a mode of sharing an experience pool by all agents under the condition of not distinguishing the agents, and then averaging parameters of all basic models to obtain initialization parameters; initialization parameters are used as initial values of decision models corresponding to different agents, and then the decision models are trained according to experience pool samples corresponding to the agents. According to the method, the generalization ability and the convergence efficiency of the decision model are greatly improved by using the initialization parameters. 本发明提出了一种面向异质任务泛化的边缘缓存调度、任务卸载方法和系统。本发明公开了一种面向异质任务泛化的边缘缓存调度方法，首先在不区分智能体的情况下，采用所有智能体共用经验池的方式对基础模型进行训练，然后通过所有基础模型的参数平均获得初始化参数；本发明中以初始化参数为不同智能