Report
Predictive Resource Allocation for URLLC using Empirical Mode Decomposition
| العنوان: | Predictive Resource Allocation for URLLC using Empirical Mode Decomposition |
|---|---|
| المؤلفون: | Jayawardhana, Chandu, Sivalingam, Thushan, Mahmood, Nurul Huda, Rajatheva, Nandana, Latva-Aho, Matti |
| سنة النشر: | 2023 |
| مصطلحات موضوعية: | Electrical Engineering and Systems Science - Signal Processing |
| الوصف: | Effective resource allocation is a crucial requirement to achieve the stringent performance targets of ultra-reliable low-latency communication (URLLC) services. Predicting future interference and utilizing it to design efficient interference management algorithms is one way to allocate resources for URLLC services effectively. This paper proposes an empirical mode decomposition (EMD) based hybrid prediction method to predict the interference and allocate resources for downlink based on the prediction results. EMD is used to decompose the past interference values faced by the user equipment. Long short-term memory and auto-regressive integrated moving average methods are used to predict the decomposed components. The final predicted interference value is reconstructed using individual predicted values of decomposed components. It is found that such a decomposition-based prediction method reduces the root mean squared error of the prediction by $20 - 25\%$. The proposed resource allocation algorithm utilizing the EMD-based interference prediction was found to meet near-optimal allocation of resources and correspondingly results in $2-3$ orders of magnitude lower outage compared to state-of-the-art baseline prediction algorithm-based resource allocation. Comment: Accepted for European Conference on Networks and Communications (EUCNC) and 6G Summit-2023, Gothenburg, Sweden |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2304.01696 |
| رقم الانضمام: | edsarx.2304.01696 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |