Blind Load-Balancing Algorithm using Double-Q- learning in the Fog Environment

In the distributed fog computing infrastructure, fog nodes can process user requests locally. In order to reduce the delay and response time of user requests, incoming requests must be evenly distributed among fog nodes. For this purpose, in this paper, we propose a new method to improve the load-balancing in the fog environment. In the proposed algorithm, the mobile device sends a task to a fog node. Then the fog node decides to process that task using the Double-Q-learning algorithm. One of the critical advantages of the proposed algorithm in this paper is that decision-making on tasks is done without any knowledge of the state of neighboring nodes. The results show that the proposed algorithm with proper distribution of tasks between nodes significantly reduces the delay and response time to the user than compared methods.