Predictive Traffic Control and Differentiation on Smart Grid Neighborhood Area Networks

Abstract

Smart Grid (SG) networks include an associated data network for the transmission and reception of control data related to the electric power supply service. A subset of this data network is the SG Neighborhood Area Network (SG NAN), whose objective is to interconnect the subscribers' homes with the supplier control center. The data flows transmitted through these SG NANs belong to different applications, giving rise to the need for different quality of service requirements. Additionally, other subscriber appliances could use this network to communicate over the Internet. To avoid network congestion, as well as to differentiate the quality of service (QoS) received by the different data flows, a congestion control mechanism with traffic differentiation capabilities is required. The main contribution of this work is the proposal of a new congestion control mechanism based on machine learning techniques to try to guarantee the different QoS requirements to the different data flows. A main problem when applying machine learning techniques is the need for datasets to be used in the training steps. In this sense, a second contribution of this article is the proposal of a method to generate such datasets by means of simulation techniques. The proposed mechanism is then evaluated in the context of a wireless SG NAN. The nodes of this network are the subscriber's smart meters, which in turn perform the function of concentrating the data traffic sent and received by the rest of the home appliances. Besides, different machine learning classification methods are taken into account. The evaluation carried out shows significant improvements in terms of network throughput, transit time, and quality of service differentiation. Finally, the computational cost of the algorithms used in this proposal has also been evaluated, using real low-cost IoT hardware platforms.

A Reinforcement Learning Congestion Control Algorithm for Smart Grid Networks

“…Within the scope of UDP-based network systems for smart grids, the decision tree-based congestion control (DTCC) mechanism and the neural network congestion control (NNCC) are introduced in [1]. The first mechanism employs machine learning to predict and adjust to network congestion.…”

“…effective, scalable, and easy to deploy, making them a popular choice for enhancing the capabilities of utility networks. In particular, multi-hop wireless networks, known for their flexibility and adaptability, are considered suitable options for smart grid communications [1]- [5].…”

“…Without a feedback mechanism during network congestion, UDP can cause network performance degradation. Several solutions have been proposed to solve this problem, some based on machine learning techniques [1]- [3], [6]. Unlike supervised learning, which requires a time-consuming process of collecting labeled data sets, reinforcement learning (RL) offers a notable advantage.…”

Novel Road Traffic Management Strategy for Rapid Clarification of the Emergency Vehicle Route Based on V2V Communications

“…Furthermore, machine learning was considered as one of the promising techniques to control traffic congestion and, at the same time, to attempt to guarantee the system’s quality-to-service requirements. Machine learning requires large datasets to be used in the training steps which is solved in [ 18 ].…”

Topology-Based Machine Learning: Predicting Power Line Communication Quality in Smart Grids

“…Channel models are mainly categorized into two families: (i) bottom-up approaches, which use physically realistic models to understand channel behavior [15], [16]; (ii) top-down approaches look at real measurements to optimize generation of physical channel implementations [17]- [19]. Machine Learning (ML) approaches to top-down models can be found in [20], [21]. A complete overview on ML approaches for PLC can be found in [22].…”