Abstract
The future high-speed cellular networks require efficient and high-speed handover mechanisms. However, the traditional cellular handovers are based upon measurements of target cell radio strength which requires frequent measurement gaps. During these measurement windows, data transmission ceases each time, while target bearings are measured causing serious performance degradation. Therefore, prediction-based handover techniques are preferred in order to eliminate frequent measurement windows. Thus, this work proposes an ultrafast and efficient XGBoost-based predictive handover technique for next generation mobile communications. The ML algorithm in general prefers 70–30% of training and test data, respectively. However, always obtaining 70% of training samples in mobile communications is challenging because the channel remains correlated within coherence time only. Therefore, collecting training samples beyond coherence time limits performance and adds delay; thus, the proposed work trains the model within coherence time where this fixed data split of 70–30% makes the model exceed coherence time. Despite the fact that the proposed model gets starved of required training samples, still there is no loss in predication accuracy. The test results show a maximum delay improvement of up to 596 ms with enhanced performance efficiency of 68.70% depending upon the scenario. The proposed model reduces delay and improves efficiency by having an appropriate training period; thus, the intelligent technique activates faster with improved accuracy and eliminates delay in the algorithm to predict mmWaves’ signal strength in contrast to actually measuring them.
Highlights
Saad Ijaz Majid,1,2 Syed Waqar Shah,1 Safdar Nawaz Khan Marwat,3 Abdul Hafeez,4 Haider Ali,2 and Naveed Jan 5
The ML algorithm preferably requires 70% of training samples, while the proposed algorithm requires these samples to be collected within channel coherence time. is concept works best till Tsim ≤ 200 ms but as soon Tsim gets greater than 200 ms, channel coherence time gets small enough where collection of 70% of training samples gets impossible to be collected within Tc. e contest arises that
BS Level Analysis. is section provides detailed analysis at the BS level; Table 10 shows that, by selecting the proposed training sequence (Tr), which is referred to as the correct training sequence in this work, the model response time can be significantly improved without trading off HSR or accuracy by not even taking 70% of required samples
Summary
Saad Ijaz Majid ,1,2 Syed Waqar Shah ,1 Safdar Nawaz Khan Marwat ,3 Abdul Hafeez ,4 Haider Ali ,2 and Naveed Jan 5. Us, this work proposes an ultrafast and efficient XGBoost-based predictive handover technique for generation mobile communications. (1) Determination of proper channel coherence time (2) Accurate training period of the model (3) Improved delay and the proposed algorithm activates much faster (4) Less memory consumption because number of samples are reduced (5) Utilization of error control in the XGBoost algorithm (6) Eliminate oversampling (7) Reduced learning period, which eliminates underutilization, and the model executes more handover decisions e paper is further organized in such a manner that Section 1 introduces the problem and literature review, Section 2 details the proposed solution, Section 3 discusses results, and Section 4 provides conclusion of the proposed work. E literature above highlights some of the classical techniques used to determine radio bearings of a target cell All these algorithms are MG dependent, and there is no novelty where an unwanted MG can be avoided through prior prediction of mmWaves’ signal strength by exploiting out-of-band information that is already available. Erefore, the UEs are plotted such that S(u) is stochastic with the process rate of λ having probability of Q in time u where B is output of an arbitrary function defined by limj⟶0(B(j)/j) 0. en, mathematically,
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
