Support Vector Regression to Downscaling Climate Big Data: An Application for Precipitation and Temperature Future Projection Assessment

2019 ◽

Vol 9 (1) ◽

pp. 4162-4171

Keyword(s):

Big Data ◽

Load Balancing ◽

Response Time ◽

Support Vector Regression ◽

Virtual Machine ◽

Data Centers ◽

Migration Time ◽

Support Vector ◽

Load Balancer ◽

Cloud User

The process of analyzing big data and other valuable information is a significant process in the cloud. Since big data processing utilizes a large number of resources for completing certain tasks. Therefore, the incoming tasks are allocated with better utilization of resources to minimize the workload across the server in the cloud. The conventional load balancing technique failed to balance the load effectively among data centers and dynamic QoS requirements of big data application. In order to improve the load balancing with maximum throughput and minimum makespan, Support Vector Regression based MapReduce Throttled Load Balancing (SVR-MTLB) technique is introduced. Initially, a large number of cloud user requests (data/file) are sent to the cloud server from different locations. After collecting the cloud user request, the SVR-MTLB technique balances the workload of the virtual machine with the help of support vector regression. The load balancer uses the index table for maintaining the virtual machines. Then, map function performs the regression analysis using optimal hyperplane and provides three resource status of the virtual machine namely overloaded, less loaded and balanced load. After finding the less loaded VM, the load balancer sends the ID of the virtual machine to the data center controller. The controller performs migration of the task from an overloaded VM to a less loaded VM at run time. This in turn assists to minimize the response time. Experimental evaluation is carried out on the factors such as throughput, makespan, migration time and response time with respect to a number of tasks. The experimental results reported that the proposed SVR-MTLB technique obtains high throughput with minimum response time, makespan as well as migration time than the state -of -the -art methods.

Download Full-text

Data-Driven Prediction of Vessel Propulsion Power Using Support Vector Regression with Onboard Measurement and Ocean Data

Sensors ◽

10.3390/s20061588 ◽

2020 ◽

Vol 20 (6) ◽

pp. 1588 ◽

Cited By ~ 4

Author(s):

Donghyun Kim ◽

Sangbong Lee ◽

Jihwan Lee

Keyword(s):

Big Data ◽

Support Vector Regression ◽

Operating Conditions ◽

Data Driven ◽

Superior Performance ◽

Support Vector ◽

Power Prediction ◽

Static Water ◽

Data Driven Approach ◽

Propulsion Power

The fluctuation of the oil price and the growing requirement to reduce greenhouse gas emissions have forced ship builders and shipping companies to improve the energy efficiency of the vessels. The accurate prediction of the required propulsion power at various operating condition is essential to evaluate the energy-saving potential of a vessel. Currently, a new ship is expected to use the ISO15016 method in estimating added resistance induced by external environmental factors in power prediction. However, since ISO15016 usually assumes static water conditions, it may result in low accuracy when it is applied to various operating conditions. Moreover, it is time consuming to apply the ISO15016 method because it is computationally expensive and requires many input data. To overcome this limitation, we propose a data-driven approach to predict the propulsion power of a vessel. In this study, support vector regression (SVR) is used to learn from big data obtained from onboard measurement and the National Oceanic and Atmospheric Administration (NOAA) database. As a result, we show that our data-driven approach shows superior performance compared to the ISO15016 method if the big data of the solid line are secured.

Download Full-text

Attribution and Prediction of Precipitation and Temperature Trends within the Sydney Catchment Using Machine Learning

Climate ◽

10.3390/cli8100120 ◽

2020 ◽

Vol 8 (10) ◽

pp. 120

Author(s):

Joshua Hartigan ◽

Shev MacNamara ◽

Lance M. Leslie ◽

Milton Speer

Keyword(s):

Machine Learning ◽

Linear Regression ◽

Water Supply ◽

Regression Model ◽

Support Vector Regression ◽

Skill Score ◽

Annual Precipitation ◽

Support Vector ◽

Temperature Trends ◽

Precipitation And Temperature

Droughts in southeastern Australia can profoundly affect the water supply to Sydney, Australia’s largest city. Increasing population, a warming climate, land surface changes and expanded agricultural use increase water demand and reduce catchment runoff. Studying Sydney’s water supply is necessary to manage water resources and lower the risk of severe water shortages. This study aims at understanding Sydney’s water supply by analysing precipitation and temperature trends across the catchment. A decreasing trend in annual precipitation was found across the Sydney catchment area. Annual precipitation also is significantly less variable, due to fewer years above the 80th percentile. These trends result from significant reductions in precipitation during spring and autumn, especially over the last 20 years. Wavelet analysis was applied to assess how the influence of climate drivers has changed over time. Attribute selection was carried out using linear regression and machine learning techniques, including random forests and support vector regression. Drivers of annual precipitation included Niño3.4, Southern Annular Mode (SAM) and DMI, and measures of global warming such as the Tasman Sea sea surface temperature anomalies. The support vector regression model with a polynomial kernel achieved correlations of 0.921 and a skill score compared to climatology of 0.721. The linear regression model also performed well with a correlation of 0.815 and skill score of 0.567, highlighting the importance of considering both linear and non-linear methods when developing statistical models. Models were also developed on autumn and winter precipitation but performed worse than annual precipitation on prediction. For example, the best performing model on autumn precipitation, which accounts for approximately one quarter of annual precipitation, achieved an RMSE of 418.036 mm2 on the testing data, while annual precipitation achieved an RMSE of 613.704 mm2. However, the seasonal models provided valuable insights into whether the season would be wet or dry compared to the climatology.

Download Full-text