Dynamic Network Slice Scaling Assisted by Attention-Based Prediction in 5G Core Network

Network slicing is a key technology in fifth-generation (5G) networks that allows network operators to create multiple logical networks over a shared physical infrastructure to meet the requirements of diverse use cases. Among core functions to implement network slicing, resource management and scaling are difficult challenges. Network operators must ensure the Service Level Agreement (SLA) requirements for latency, bandwidth, resources, etc for each network slice while utilizing the limited resources efficiently, i.e., optimal resource assignment and dynamic resource scaling for each network slice. Existing resource scaling approaches can be classified into reactive and proactive types. The former makes a resource scaling decision when the resource usage of virtual network functions (VNFs) exceeds a predefined threshold, and the latter forecasts the future resource usage of VNFs in network slices by utilizing classical statistical models or deep learning models. However, both have a trade-off between assurance and efficiency. For instance, the lower threshold in the reactive approach or more marginal prediction in the proactive approach can meet the requirements more certainly, but it may cause unnecessary resource wastage. To overcome the trade-off, we first propose a novel and efficient proactive resource forecasting algorithm. The proposed algorithm introduces an attention-based encoder-decoder model for multivariate time series forecasting to achieve high short-term and long-term prediction accuracies. It helps network slices be scaled up and down effectively and reduces the costs of SLA violations and resource overprovisioning. Using the attention mechanism, the model attends to every hidden state of the sequential input at every time step to select the most important time steps affecting the prediction results. We also designed an automated resource configuration mechanism responsible for monitoring resources and automatically adding or removing VNF instances.

View this article on IEEE Xplore

 

Dengue Epidemics Prediction: A Survey of the State-of-the-Art based on Data Science Processes

Dengue infection is a mosquito-borne disease caused by dengue viruses, which are carried by several species of mosquito of the genus Aedes, principally Ae. aegypti. Dengue outbreaks are endemic in tropical and sub-tropical regions of the world, mainly in urban and sub-urban areas. The outbreak is one of the top ten diseases causing the most deaths worldwide. According to the World Health Organization (WHO), dengue infection has increased 30-fold globally over the past five decades. About 50 to 100 million new infections occur annually in more than 80 countries. Many researchers are working on measures to prevent and control the spread. One avenue of research is collaboration between computer science and the epidemiology researchers in developing methods of predicting potential outbreaks of dengue infection. An important research objective is to develop models that enable, or enhance, forecasting of outbreaks of dengue, giving medical professionals the opportunity to develop plans for handling the outbreak, well in advance. Researchers have been gathering and analyzing data to better identify the relational factors driving the spread of the disease, as well as the development of a variety of methods of predictive modelling using statistical and mathematical analysis and Machine Learning. In this substantial review of the literature on the state of the art of research over the past decades, we identified six main issues to be explored and analyzed: (1) The available data sources, (2) Data preparation techniques, (3) Data representations, (4) Forecasting models and methods, (5) Dengue forecasting models evaluation approaches, and (6) Future challenges and possibilities in forecasting modelling of dengue outbreaks. Our comprehensive exploration of the issues provides a valuable information foundation for new researchers in this important area of public health research and epidemiology.

View this article on IEEE Xplore