Centralized Energy Prediction in Wireless Sensor Networks Leveraged by Software-Defined Networking

Abstract

Resource Constraints in Wireless Sensor Networks are a key factor in protocols and application design. Furthermore, energy consumption plays an important role in protocols decisions, such as routing metrics. In Software-Defined Networking (SDN)-based networks, the controller is in charge of all control and routing decisions. Using energy as a metric requires such information from the nodes, which would increase packets traffic, impacting the network performance. Previous works have used energy prediction techniques to reduce the number of packets exchanged in traditional distributed routing protocols. We applied this technique in Software-Defined Wireless Sensor Networks (SDWSN). For this, we implemented an energy prediction algorithm for SDWSN using Markov chain. We evaluated its performance executing the prediction on every node and on the SDN controller. Then, we compared their results with the case without prediction. Our results showed that by running the Markov chain on the controller we obtain better prediction and network performance than when running the predictions on every node. Furthermore, we reduced the energy consumption for topologies up to 49 nodes for the case without prediction.

SSDWSN: A Scalable Software-Defined Wireless Sensor Networks

“…In addition, we propose predicting the continuous transmission of local information from the sensor nodes to the controller to minimize excessive energy loss and traffic overhead. Although the Markov chain and sensor node state have been used in some studies to predict node residual energy levels [10], [13], [41], our approach distinguishes itself by using DRL to handle complexity and uncertainty within SDWSN. This enables our approach to learn directly from high-dimensional network traffic data without explicitly requiring knowledge of underlying dynamics.…”

“…This constant need for synchronization between the network and its controller is necessary to collect comprehensive traffic statistics [6]. These statistics are vital for maintaining network efficiency and reliability and significantly affect the scalability and operational efficiency of SDWSNs [10]- [13]. However, maintaining this level of network insight and control necessitates regular updates, resulting in an increased volume of controller-bound traffic.…”

A survey on Machine Learning Software-Defined Wireless Sensor Networks (ML-SDWSNs): Current status and major challenges

“…The controller predicts the individual energy consumption of sensor nodes; thus, sensor nodes avoid reporting energy levels to the controller. Nunez et al [161] proposed a Markov chain prediction mechanism for SDWSNs. They compared the prediction model by running it on every sensor node of the WSN and solely in the controller.…”

A survey on Machine Learning Software-Defined Wireless Sensor Networks (ML-SDWSNs): Current status and major challenges

“…The controller predicts the individual energy consumption of sensor nodes; thus, sensor nodes avoid reporting energy levels to the controller. Nunez Segura and Borges Margi [161] proposed a Markov chain prediction mechanism for SDWSNs. They compared the prediction model by running it on every sensor node of the WSN and solely in the controller.…”