Cloud computing is becoming popular. Build high-quality cloud applications is a critical research problem. QoS rankings provide valuable information for make optimal cloud service selection from a set of functionally equivalent service candidates. To obtain Qos values real-world invocations the service candidates are usually required based on the Cloud Broker. To avoid the time consuming and expensive real-world service invocations, It proposes a QoS ranking prediction framework for cloud services by taking an advantage of the past service usage experiences of other consumers. Our proposed framework requires no need additional invocations of cloud services when making QoS ranking prediction by cloud broker service provider. Two personalized QoS ranking prediction approaches are proposed to predict the QoS rankings directly based on cost and ranking. Comprehensive experiments are conducted employing real-world QoS data, including 300 distributed users and 500 real world web services to all over the world. The experimental results show that our approaches outperform other competing approaches.