A Machine Learning Approach to Achieving Energy Efficiency in Relay-Assisted LTE-A Downlink System

Hassan, Hammad; Ahmed, Irfan; Ahmad, Rizwan; Khammari, Hédi; Bhatti, Ghulam; Ahmed, Waqas; Alam, Muhammad Mahtab

doi:10.3390/s19163461

Cited by 8 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MATLAB ® Deep Learning Toolbox TM was adopted to develop and train a NN aimed at predicting the drone flight time over a corner out of the defined classes. A feedforward NN was implemented and the Bayesian regularization backpropagation algorithm [41] was adopted to train the NN, which achieved better generalization performance, considering the data variability [42]. The selected input parameters were the normalized following ones:…”

Section: Methods Based On Machine Learningmentioning

confidence: 99%

Drone Trajectory Segmentation for Real-Time and Adaptive Time-Of-Flight Prediction

Conte

Alteriis

Moriello

et al. 2021

Drones

View full text Add to dashboard Cite

This paper presents a method developed to predict the flight-time employed by a drone to complete a planned path adopting a machine-learning-based approach. A generic path is cut in properly designed corner-shaped standard sub-paths and the flight-time needed to travel along a standard sub-path is predicted employing a properly trained neural network. The final flight-time over the complete path is computed summing the partial results related to the standard sub-paths. Real drone flight-tests were performed in order to realize an adequate database needed to train the adopted neural network as a classifier, employing the Bayesian regularization backpropagation algorithm as training function. For the network, the relative angle between two sides of a corner and the wind condition are the inputs, while the flight-time over the corner is the output parameter. Then, generic paths were designed and performed to test the method. The total flight-time as resulting from the drone telemetry was compared with the flight-time predicted by the developed method based on machine learning techniques. At the end of the paper, the proposed method was demonstrated as effective in predicting possible collisions among drones flying intersecting paths, as a possible application to support the development of unmanned traffic management procedures.

show abstract

Section: Methods Based On Machine Learningmentioning

confidence: 99%

Drone Trajectory Segmentation for Real-Time and Adaptive Time-Of-Flight Prediction

Conte

Alteriis

Moriello

et al. 2021

Drones

View full text Add to dashboard Cite

show abstract

“…A pair (𝑘, 𝑛) ≠ 𝜇 𝑇𝐴 , where 𝑛∈𝓝, 𝑘∈𝓚 is said to be a blocking pair for the matching 𝜇 𝑇𝐴 if it is not blocked by an individual tag 𝑘 and PU 𝑛, and there exists another matching 𝜇 𝑇𝐴 ′ ∈ 𝜇 𝑇𝐴 (𝑘, 𝑛) such that IoT tag 𝑘 and PU 𝑛 can achieve a higher utility. Hence, given fixed preference relations of IoT tags and PUs, Algorithm 1 is known as the deferred acceptance algorithm in the two-sided matching which converges to a stable matching [39], [40].…”

Section: Algorithm 1: Matching Game For Iot Tags Associationmentioning

confidence: 99%

Ambient Backscatter Communication System Empowered by Matching Game and Machine Learning for Enabling Massive IoT Over 6G HetNets

Khalifa,

El-Haleem,

Elmesalawy

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Ambient backscatter communication (ABC) is considered as a promising paradigm for meeting the 6G massive Internet of Things (IoT) requirements which is expected to revolutionize our world. In this paper, a new multimode matching game and machine learning-based IoT ambient backscatter communication scheme is proposed to maximize the ABC system rate and capacity over the LTE and Wi-Fi multi-RAT heterogeneous network, thereby supporting the 6G green massive IoT communication. The proposed algorithm is designed to support different rate and capacity requirements for different massive Machine Type Communication (mMTC) use cases such as sensor networks, smart grid, agriculture and low data rate Ultra Reliable Low Latency Communication (URLLC) use cases such as Tactile Interaction. The proposed optimization algorithm runs into two phases, the first one is a matching game-based algorithm that selects the optimum association between the IoT tags and the primary users (PU) downlink signals from a specific base station which maximizes the IoT tags rate while minimizing the resulting interference to the PU. Each IoT tag can ride the PU downlink signal using one of three different riding modes according to the required IoT ABC system rate and capacity, whereas mode 1 allows multiple IoT tags to ride the whole PU downlink signal resource blocks, in mode 2 each IoT tag can ride only one subcarrier from the PU downlink signal resource blocks, while in mode 3 multiple IoT tags can ride the same subcarrier from the PU downlink signal resource blocks. In addition, unmanned aerial vehicles (UAVs) flying HetNodes equipped with LTE and Wi-Fi receivers are used as backscatter receivers to receive the IoT tags uplink backscattered signals, so the second optimization phase is formulated to maximize the total sum rate of the ABC system by dividing its service area into clusters using the enhanced unsupervised k-means algorithm, also the enhanced k-means algorithm finds the optimum location of each cluster's serving UAV flying HetNode that maximizes the channels gain between the IoT tags and the serving UAV flying HetNode in order to maximize the total system rate. The system model was implemented within the MATLAB environment where simulations across the various scenarios are conducted to assess the effectiveness of the proposed algorithm. Simulation results and the performance analysis demonstrated that the proposed algorithm can support the required rate for the most mMTC and low data rate URLLC IoT applications with average IoT tag rates in the range of 15 Kbps to 115 Kbps, and outperforms the algorithm-free riding technique in the case of massive IoT applications. The proposed mode 2 (first enhanced mode) achieves the best performance in terms of the average IoT tags rate and the total system rate with the lowest interference to the primary system users, on the other hand, mode 3 (second enhanced mode) improves the system capacity with maximum IoT tags satisfaction ratio. The capacity and satisfaction ratio of the proposed mode 3 outp...

show abstract

“…In comparison to more conventional methods, the results showed a considerable decrease in packet latency. Hassan et al [15] studied machine learning approach to achieving energy efficiency in relay-assisted LTE-A downlink system. Energy efficiency (EE) is a motivating force in this study because of its recent rise to prominence as an important design parameter for mobile devices.…”

Section: Review Of Related Literaturementioning

confidence: 99%

Users’ Evaluation of Traffic Congestion in LTE Networks using Machine Learning Techniques

Kuboye

Adedipe

Oloja

et al. 2023

artif. intell. adv.

View full text Add to dashboard Cite

Over time, higher demand for data speed and quality of service by an increasing number of mobile network subscribers has been the major challenge in the telecommunication industry. This challenge is the result of an increasing population of human race and the continuous advancement in mobile communication industry, which has led to network traffic congestion. In an effort to solve this problem, the telecommunication companies released the Fourth Generation Long Term Evolution (4G LTE) network and afterwards the Fifth Generation Long Term Evolution (5G LTE) network that laid claims to have addressed the problem. However, machine learning techniques, which are very effective in prediction, have proven to be capable of great importance in the extraction and processing of information from the subscriber’s perceptions about the network. The objective of this work is to use machine learning models to predict the existence of traffic congestion in LTE networks as users perceived it. The dataset used for this study was gathered from some students over a period of two months using Google form and thereafter, analysed using the Anaconda machine learning platform. This work compares the results obtained from the four machine learning techniques employed that are k-Nearest Neighbour, Support Vector Machine, Decision Tree and Logistic Regression. The performance evaluation of the ML techniques was done using standard metrics to ascertain the real existence of congestion. The result shows that k-Nearest Neighbour outperforms all other techniques in predicting the existence of traffic congestion. This study therefore has shown that the majority of LTE network users experience traffic congestion.

show abstract

A Machine Learning Approach to Achieving Energy Efficiency in Relay-Assisted LTE-A Downlink System

Cited by 8 publications

References 23 publications

Drone Trajectory Segmentation for Real-Time and Adaptive Time-Of-Flight Prediction

Drone Trajectory Segmentation for Real-Time and Adaptive Time-Of-Flight Prediction

Ambient Backscatter Communication System Empowered by Matching Game and Machine Learning for Enabling Massive IoT Over 6G HetNets

Users’ Evaluation of Traffic Congestion in LTE Networks using Machine Learning Techniques

Contact Info

Product

Resources

About