Now a days, the resource allocation manages the resource networks such as bandwidth, power usage for ensuring Quality of Service (QoS) without overloading. However, the optimization fails to adapt traffic loads due to...
详细信息
ISBN:
(数字)9798331508456
ISBN:
(纸本)9798331508463
Now a days, the resource allocation manages the resource networks such as bandwidth, power usage for ensuring Quality of Service (QoS) without overloading. However, the optimization fails to adapt traffic loads due to its dependance on static resource allocation that cannot adjust to user demands and power control. To overcome this limitation in this research resource allocation method Federated-Double-Deep Q-Network (F-DDQN) is proposed for maximizing throughput and achieve minimum QoS requirements for all active Device-to-Device communication(D2D) pairs and Cellular Users (CUE). whereas Federated learning enhances adaptability to dynamically communication environments. Initially, the data is collected from D2D-enabled heterogeneous cellular networks (HetNet) dataset and 3-tier HetNet system model are designed. Further, for resource management the F-DDQN enhances the energy-efficient by decentralizing action states and minimizes communication overhead and power consumption by sharing model updates instead of raw data, and DDQN effectively improves the energy efficiency in resource allocation by estimating Q-values and optimizes resource allocation through selecting the most energy-efficient transmitting power and channels using target estimation. From the results the proposed model achieved better results to evaluate its effectiveness in increasing system throughput with 58.90% compared with both CUE and D2D Users Equipment (DUE) with existing method a Deep Q-network-based Reinforcement learning algorithm (DRL).
Now a days, the resource allocation manages the resource networks such as bandwidth, power usage for ensuring Quality of Service (QoS) without overloading. However, the optimization fails to adapt traffic loads due to...
详细信息
Nowadays, the rapid growth of predictive maintenance methods has become crucial for Internet of Things (IoT) enabled wireless devices. The existing Random Forest (RF) utilized to predict device failures although, the ...
详细信息
Nowadays, the rapid growth of predictive maintenance methods has become crucial for Internet of Things (IoT) enabled wireless devices. The existing Random Forest (RF) utilized to predict device failures although, the ...
详细信息
ISBN:
(数字)9798331508456
ISBN:
(纸本)9798331508463
Nowadays, the rapid growth of predictive maintenance methods has become crucial for Internet of Things (IoT) enabled wireless devices. The existing Random Forest (RF) utilized to predict device failures although, the complexity of IoT device data led to scalability issues. Hence, this research proposes an Adaptive Boosting with Synthetic Minority Oversampling Technique (AdaBoost-SMOTE) for predicting device failures. The proposed AdaBoost-SMOTE overcome the scalability issues by handling imbalanced data and reducing dimensionality for accurate prediction. Initially, the input data is collected from IoT-enabled sensors and preprocessed with z-score normalization to scale the features. Then, Permutation Importance (PI) is employed to select the optimal features by ranking the feature score based on its importance. After that, SMOTE is used to handle the imbalance data and then, AdaBoost is employed to predict the machine failures by assigning the higher weights to misclassified samples in an iterative manner. Finally, hyperparameter tuning is done by using Grid Search Cross-Validation (GSCV) to optimize the parameters by selecting best CV score as a best set of hyperparameters. From the results, the proposed AdaBoost-SMOTE achieved best results in terms of accuracy (97%), precision (95%), recall (93%), and F1-score (94%) when compared to existing AdaBoost.
暂无评论