Smart cities are one of the promising application areas where the energy management (supply/dispatch) issues have the potential to positively affect the society. In the common era of information and technology, the consumers expect the required amount of energy to be present at anytime. This energy is obtained through renewable and nonrenewable resources. Smart wind energy is the idea of efficient energy generation utilizing the wind while satisfying green expectations. However, the random characteristics caused by various external factors have significant effects on wind speeds, thus introducing difficulties in power systems operations and energy generation. Forecasting techniques can be effectively used to predict future wind speeds and power generation to optimize the energy output. The objective of this study is to provide a framework for a local smart-city wind energy harvesting model. Our study evaluates wind speed forecasting models based on synced weather characteristics (air temperature, humidity, and pressure), against models based on wind speed data itself. The produced models are implemented via k-nearest neighbors and linear regression. Two different data sets are addressed for performance comparison purposes. The first one is 5 years of 10-minute time span measurements at Middle East Technical University campus. The second data set is 3 years of the same time span at a site in California, USA. The accuracy of predictions is found to be higher for the data sets with lower variance (METU data set). However, the models fit the higher variance (NREL data set) data better than the lower one.