Posters

Abstract

Renewable energy sources are known to be generally intermittent in nature and location-specific. They are those natural sources that replenish themselves over a short period. Since they are location-specific, power generated from such sources is highly dependent on environmental conditions. One of the most interesting renewable energy sources is wind energy. Wind energy is interesting for power generation due to it being pollution-free and available globally. The ability to install wind turbines in many environments has significantly increased their potential to meet the ever-increasing energy demand. Technologically developed areas, such as cities, have a high potential for wind energy, as they provide numerous potential sites for turbine installation including the rooftops of high-rise buildings, railway tracks, the region between or around multi-storeyed buildings, and city roads. However, harnessing wind energy from these areas is quite challenging since the wind flow has a dramatic nature, often being chaotic and turbulent. Blade-less wind turbines that can harness winds from any direction have been developed (i.e. by O-Innovations). These attributes make it possible for wind energy to be exploited in dense urban environments where the buildings make flow patterns chaotic and difficult to harness via conventional wind turbines. This study provides a demonstration of urban wind flows and their potential for power generation. A case study has been made from the Bowland Tower (located on the Lancaster University campus (54°00'36.43''N and 2°47'06.56''E) in Lancaster, UK). Computational fluid dynamics simulations of the wind flow around this urban environment was used to complete an evaluation of the turbulent flow properties leading to estimations of the wind power distribution. To evaluate machine learning techniques for the prediction of turbulent intensity, turbulent kinetic energy, and turbulence dissipation, in urban environments generally, in this paper a new model based on Prophet Forecast Model (PFM); a time series analysis tool has been proposed and developed. Input parameters of the model include Turbulent Intensity values, Turbulent Kinetic Energy values, and Turbulence Dissipation values throughout the whole environment. The obtained results showed that the constructed model has good potential to be used as a more applicable model compared to current models in wind turbine designs and implementation.