scholarly journals Web Traffic Time Series Forecasting using ARIMA and LSTM RNN

2020 ◽  
Vol 32 ◽  
pp. 03017
Author(s):  
Tejas Shelatkar ◽  
Stephen Tondale ◽  
Swaraj Yadav ◽  
Sheetal Ahir
Keyword(s):  
Time Series ◽  
Real Time ◽  
Time Series Forecasting ◽  
Web Traffic ◽  
Time Data ◽  
Traffic Forecasting ◽  
Traffic Time Series ◽  
Breakdown Time ◽  
Server Breakdown ◽  
Multiple Domains

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;

scholarly journals Monitoring distributed computing beyond the traditional time-series histogram

2020 ◽  
Vol 245 ◽  
pp. 03036
Author(s):  
M S Doidge ◽  
P. A. Love ◽  
J Thornton
Keyword(s):  
Time Series ◽  
Distributed Computing ◽  
Real Time ◽  
A Priori ◽  
Time Data ◽  
Use Of Time ◽  
Computing Services ◽  
Monitoring Tools ◽  
Novel Approach ◽  
Current Monitoring

In this work we describe a novel approach to monitor the operation of distributed computing services. Current monitoring tools are dominated by the use of time-series histograms showing the evolution of various metrics. These can quickly overwhelm or confuse the viewer due to the large number of similar looking graphs. We propose a supplementary approach through the sonification of real-time data streamed directly from a variety of distributed computing services. The real-time nature of this method allows operations staff to quickly detect problems and identify that a problem is still ongoing, avoiding the case of investigating an issue a-priori when it may already have been resolved. In this paper we present details of the system architecture and provide a recipe for deployment suitable for both site and experiment teams.

scholarly journals Modelling New Zealand Road Deaths

2021 ◽  
Vol 32 (2) ◽  
pp. 4-15
Author(s):  
Colin Morrison ◽  
Ernest Albuquerque
Keyword(s):  
Time Series ◽  
New Zealand ◽  
Moving Average ◽  
Arima Model ◽  
Time Series Forecasting ◽  
Time Data ◽  
Baseline Model ◽  
Explanatory Variables ◽  
Distributed Lag ◽  
Autoregressive Distributed Lag

New Zealand is developing an integrated road safety intervention logic model. This paper describes a core component of this wider strategic research carried out in 2018: a baseline model that extrapolates New Zealand road deaths to 2025. The baseline will provide context to what Waka Kotahi NZ Transport Agency is trying to achieve. It offers a way of understanding what impact interventions have in acting with and against external influences affecting road deaths and serious trauma. The baseline model considers autonomous change at a macro level given social and economic factors that influence road deaths. Identifying and testing relationships and modelling these explanatory variables clarifies the effect of interventions. Time-series forecasting begins by carefully collecting and rigorously analysing sequences of discrete-time data, then developing an appropriate model to describe the inherent structure of the series. Successful time-series forecasting depends on fitting an appropriate model to the underlying time-series. Several time-series models were investigated in understanding road deaths in the New Zealand context. In the final modelling an autoregressive integrated moving average (ARIMA) model and two differing autoregressive distributed lag (ARDL) models were developed. A preferred model was identified. This ARDL model was used to project road deaths to 2025.

scholarly journals SYSTEM FOR ANALYSIS, RESEARCH AND FORECAST OF EVENTS IN DISCRETE TIME DATA SEQUENCES

2021 ◽  
Vol 3 (1) ◽  
pp. 61-66
Author(s):  
Ihor Farmaha ◽  
◽  
Viktor Hadomskyi ◽  
Keyword(s):  
Time Series ◽  
Programming Language ◽  
Discrete Time ◽  
Time Series Forecasting ◽  
Time Data ◽  
Sarima Model ◽  
Python Programming Language ◽  
Develop Software ◽  
Python Programming

This paper is devoted develop software for time series forecasting using Python programming language. SARIMA model was used to develop the system.

A distributed real-time data prediction framework for large-scale time-series data using stream processing

2017 ◽  
Vol 10 (2) ◽  
pp. 145-165 ◽  
Author(s):  
Kehe Wu ◽  
Yayun Zhu ◽  
Quan Li ◽  
Ziwei Wu
Keyword(s):  
Time Series ◽  
Real Time ◽  
Large Scale ◽  
Time Series Data ◽  
Data Sources ◽  
Series Data ◽  
Time Data ◽  
Content Type ◽  
Data Prediction ◽  
Real Time Data

Purpose The purpose of this paper is to propose a data prediction framework for scenarios which require forecasting demand for large-scale data sources, e.g., sensor networks, securities exchange, electric power secondary system, etc. Concretely, the proposed framework should handle several difficult requirements including the management of gigantic data sources, the need for a fast self-adaptive algorithm, the relatively accurate prediction of multiple time series, and the real-time demand. Design/methodology/approach First, the autoregressive integrated moving average-based prediction algorithm is introduced. Second, the processing framework is designed, which includes a time-series data storage model based on the HBase, and a real-time distributed prediction platform based on Storm. Then, the work principle of this platform is described. Finally, a proof-of-concept testbed is illustrated to verify the proposed framework. Findings Several tests based on Power Grid monitoring data are provided for the proposed framework. The experimental results indicate that prediction data are basically consistent with actual data, processing efficiency is relatively high, and resources consumption is reasonable. Originality/value This paper provides a distributed real-time data prediction framework for large-scale time-series data, which can exactly achieve the requirement of the effective management, prediction efficiency, accuracy, and high concurrency for massive data sources.

scholarly journals Time-Series Photometry: CCDs vs. PMTs

1993 ◽  
Vol 136 ◽  
pp. 311-317
Author(s):  
T.J. Kreidl
Keyword(s):  
Time Series ◽  
Real Time ◽  
Complex Analysis ◽  
Compact Objects ◽  
Time Data ◽  
Photoelectric Photometry ◽  
Analysis Techniques ◽  
Periodicity Analysis ◽  
Profile Fitting ◽  
Comparison Stars

AbstractWith the ability to obtain simultaneous photometry of many objects, CCD time-series photometry is a potentially powerful method for obtaining data, even under non-photometric conditions. In particular, the ability to utilize one or more comparison stars on the same frame without the need to move the telescope to a different field makes for a higher duty cycle than conventional photoelectric photometry. In addition, the ability to determine the local sky in a variety of ways plus the ability to use more complex analysis techniques such as profile fitting and curves of growth permits a variety of analysis options. Some of the advantages of utilizing CCDs and the techniques used in time-series photometry of compact objects are discussed. With the flexibility of modern CCD control systems, possibilities for real-time or near real-time data analysis using readily available computer technology are stressed. Brief discussions of periodicity analysis considerations and other aspects of the data acquisition are presented.

scholarly journals COVIDSpread: real-time prediction of COVID-19 spread based on time-series modelling

F1000Research ◽  
2021 ◽  
Vol 10 ◽  
pp. 1110
Author(s):  
Siroos Shahriari ◽  
Taha Hossein Rashidi ◽  
AKM Azad ◽  
Fatemeh Vafaee
Keyword(s):  
Time Series ◽  
Real Time ◽  
Time Window ◽  
Time Series Models ◽  
Data Streaming ◽  
Time Data ◽  
Time Prediction ◽  
Time Series Modelling ◽  
Short Run ◽  
Modelling Techniques

A substantial amount of data about the COVID-19 pandemic is generated every day. Yet, data streaming, while considerably visualized, is not accompanied with modelling techniques to provide real-time insights. This study introduces a unified platform, COVIDSpread, which integrates visualization capabilities with advanced statistical methods for predicting the virus spread in the short run, using real-time data. The platform uses time series models to capture any possible non-linearity in the data. COVIDSpread enables lay users, and experts, to examine the data and develop several customized models with different restrictions such as models developed for a specific time window of the data. COVIDSpread is available here: http://vafaeelab.com/COVID19TS.html.

scholarly journals Real-time time-series modelling for prediction of COVID-19 spread and intervention assessment

2020 ◽  
Author(s):  
Taha Hossein Rashidi ◽  
Siroos Shahriari ◽  
AKM Azad ◽  
Fatemeh Vafaee
Keyword(s):  
Time Series ◽  
Real Time ◽  
Time Window ◽  
Data Streaming ◽  
Time Data ◽  
Social Distancing ◽  
Time Series Modelling ◽  
Short Run ◽  
Modelling Techniques ◽  
Effective Policy

AbstractSubstantial amount of data about the COVID-19 pandemic is generated every day. Yet, data streaming, while considerably visualized, is not accompanied with advanced modelling techniques to provide real-time insights. This study introduces a unified platform which integrates visualization capabilities with advanced statistical methods for predicting the virus spread in the short run, using real-time data. The platform is backed up by advanced time series models to capture any possible non-linearity in the data which is enhanced by the capability of measuring the expected impact of preventive interventions such as social distancing and lockdowns. The platform enables lay users, and experts, to examine the data and develop several customized models with different restriction such as models developed for specific time window of the data. Our policy assessment of the case of Australia, shows that social distancing and travel ban restriction significantly affect the reduction of number of cases, as an effective policy.

Sign in / Sign up

Export Citation Format

Share Document