Congestion Control and Prediction Schemes Using Fuzzy Logic System with Adaptive Membership Function in Wireless Sensor Networks

Abstract

Network congestion is a key challenge in resource-constrained networks, particularly those with limited bandwidth to accommodate high-volume data transmission, which causes unfavorable quality of service, including effects such as packet loss and low throughput. This challenge is crucial in wireless sensor networks (WSNs) with restrictions and constraints, including limited computing power, memory, and transmission due to self-contained batteries, which limit sensor node lifetime. Determining a path to avoid congested routes can prolong the network. Thus, we present a path determination architecture for WSNs that takes congestion into account. The architecture is divided into 3 stages, excluding the final criteria for path determination: (1) initial path construction in a top-down hierarchical structure, (2) path derivation with energy-aware assisted routing, and (3) congestion prediction using exponential smoothing. With several factors, such as hop count, remaining energy, buffer occupancy, and forwarding rate, we apply fuzzy logic systems to determine proper weights among those factors in addition to optimizing the weight over the membership functions using a bat algorithm. The simulation results indicate the superior performance of the proposed method in terms of high throughput, low packet loss, balancing the overall energy consumption, and prolonging the network lifetime compared to state-of-the-art protocols.

Soft Computing-Based Congestion Control Schemes in Wireless Sensor Networks: Research Issues and Challenges

“…In [19], a path determination architecture is presented for wireless sensor networks considering the congestion issue. The architecture comprises initial path construction in a hierarchical structure, path derivation with energy-aware assisted routing, and congestion prediction using exponential smoothing.…”

A Routing Delay Reduction Mechanism Based on Dynamic Switching through Congestion Prediction in Wireless Mobile Network

“… Congestion Prediction: It is an extremely significant way to control congestion [2]. If it is predictable early, his control will be more effective.…”

“…Due to the increasing demand for communications in various fields from text data to multimedia data at the same rate, the transmission rate also increased. Increasing the data rate causes congestion in the network and at the same time reducing the rate leads to reduced throughput and quality of service, which is a research challenge in the wireless network [1], [2], [3]. They are more complex and challenging in MANET due to dynamic nature, resource constraints and dependency on intermediate nodes.…”

“…Congestion is often caused by excessive input of the traffic rate into limited network bandwidth and congestion control methods limit this traffic rate to prevent congestion [2], [5]. The harmful characteristic of MANET makes it difficult to provide long network stability with low congestion and overhead [4], [6].…”

Bounded Interval Fuzzy Control for Half Vehicle’s Active Suspension System

“…In the vehicle suspension system the uncertainty might come into the control system from many resources such as the random road surfaces and changing in the environmental conditions. In addition, some uncertainties might be occurred due to MSF and fuzzy rules because different fuzzy rules and MSF will yield to different results [24][25][26][27]. Some researchers were proposed two layers fuzzy system which is similar to the neural network in the shape but it does not form the neural nodes [28,29].…”