REED: Enhanced Resource Allocation and Energy Management in SDN-Enabled Edge Computing-Based Smart Buildings

The number of applications of internet of things (IoT) devices in smart buildings keeps growing continuously, and with it, the computational tasks rendered by those devices. In smart buildings, IoT devices generate massive data traffic, and the number of devices and traffic volume increases exponentially. This issue is more sensitive in smart buildings as the management of their data is critical. Therefore, matching the task's differential needs (e.g., energy, delay) with the network resources is paramount. In a device-to-device (D2D) aided edge computing (EC) architecture, tasks can be offloaded to the resource-rich IoT device or edge node to improve offloading efficiency and minimize energy consumption and delay. Exploiting these benefits, in this paper, we propose enhanced resource allocation and energy management in smart buildings enabled by software-defined networking and EC, as well as D2D aided end-to-end communications (REED). REED aims to minimize energy consumption and delay in a smart building by jointly optimizing resource allocation and offloading decisions. To find the near-optimal solution, we use the model-free deep reinforcement learning, i.e., deep deterministic policy gradient algorithm, because the formulated problem is a mixed-integer nonlinear optimization problem with a large dimensional continuous state and action spaces in a dynamic environment. Simulation results show that the intended REED model can perform better in terms of energy consumption and delay than the other benchmark approaches.