Web Traffic Time Series Forecasting using ARIMA and LSTM RNN

Nowadays, web traffic forecasting is a major problem as this can cause setbacks to the workings of major websites. Time-series forecasting has been a hot topic for research. Predicting future time series values is one of the most difficult problems in the industry. The time series field encompasses many different issues, ranging from inference and analysis to forecasting and classification. Forecasting the network traffic and displaying it in a dashboard that updates in real-time would be the most efficient way to convey the information. Creating a Dashboard would help in monitoring and analyzing real-time data. In this day and age, we are too dependent on Google server but if we want to host a server for large users we could have predicted the number of users from previous years to avoid server breakdown. Time Series forecasting is crucial to multiple domains. ARIMA; LSTM RNN; web traffic; prediction;time series;

Computation of Traffic Time Series for Large Populations of IoT Devices

The Internet of Things (IoT) contains sets of hundreds of thousands of network-enabled devices communicating with central controlling nodes or information collectors. The correct behaviour of these devices can be monitored by inspecting the traffic that they create. This passive monitoring methodology allows the detection of device failures or security breaches. However, the creation of hundreds of thousands of traffic time series in real time is not achievable without highly optimised algorithms. We herein compare three algorithms for time-series extraction from traffic captured in real time. We demonstrate how a single-core central processing unit (CPU) can extract more than three bidirectional traffic time series for each one of more than 20,000 IoT devices in real time using the algorithm DStries with recursive search. This proposal also enables the fast reconfiguration of the analysis computer when new IoT devices are added to the network.

Wavelet-analysis of network traffic time-series for detection of attacks on digital production infrastructure

Digital production integrates with all the areas of human activity including critical industries, therefore the task of detecting network attacks has a key priority in protecting digital manufacture systems. This article offers an approach for analysis of digital production security based on evaluation of a posteriori probability for change point in time-series, which are based on the change point coefficient values of digital wavelet-transform in the network traffic time-series. These time-series make it possible to consider the network traffic from several points of view at the same time, which plays an important role in the task of detecting network attacks. The attack methods vary significantly; therefore, in order to detect them it is necessary to monitor different values of various traffic parameters. The proposed method has demonstrated its efficiency in detecting network service denial attacks (SlowLoris and HTTP DoS) being realized at the application level.