Time series analysis is a statistical method used in analyzing the data indexed in time. Since its first usage, the time series analysis has been widely used in scientific research and industry oriented applications. This chapter focuses on univariate time series based workload forecasting. A univariate time series is a collection of measurements of the same variable over time. The essential characteristic of any time series data is that the order of observation matters and change in order may alter the significance of the data. The time series analysis is typically associated with the process of finding a model to fit the time series data. The observed model can be used to extract the pattern, forecast future events, and to explain the affects of past events on future. This chapter discusses the five basic time series analysis models and uses them to forecast the different type of workloads on cloud servers. A detailed analysis is conducted to validate their performance on real-world data traces.