Abstract-One of the key features of high speed WLAN such as 802.11n is the use of MIMO (Multiple Input Multiple Output) antenna technology. The MIMO channel is described with fine granularity by Channel State Information (CSI) that can be utilized in various ways to maximize the network performance. Many complex parameters of a MIMO system require numerous samples to obtain CSI for all possible channel configurations. As a result, measuring the complete CSI space requires excessive sampling overhead and thus degrades the network performance. We propose CSI-SF (CSI with Sampling & Fusion), a method for estimating CSI using a small number of frame transmissions and extrapolating data to settings that have not been sampled. For instance, we predict CSI of multiple stream settings using CSI obtained only from single stream packets. We evaluate the effectiveness of CSI-SF on various network scenarios using our 802.11n testbed and show that CSI-SF provides an accurate, complete knowledge of the MIMO channel with reduced overhead from traditional sampling. We also show that CSI-SF can be applied to network algorithms such as rate adaptation, antenna selection and association control to significantly improve their performance and efficiency.The new IEEE 802.11n [1] and the emerging IEEE 802.11ac [2] standards aim to provide very high throughput WLAN to meet this growing demand of applications and services. Some of the key enhancements used for increasing the throughput are using wider, bonded channels (40 MHz in 802.11n and up to 160 MHz in 802.11ac), frame aggregation and block acknowledgments, a short guard interval, and MIMO (Multiple Input Multiple Output) antennas [3], [4]. MIMO is a popular technology in wireless communications (e.g., 802.11n, WiMax, 3GPP LTE, etc.) to increase link throughput and distance. 802.11n devices in the current market support up to three MIMO spatial streams.Algorithms and protocols for WLAN need to consider the new features offered by multiple antennas; for instance, rate adaptation is not only selecting modulation and coding rate but also the number of concurrent spatial data streams transmitted. In order to achieve optimal WLAN performance, we require a detailed knowledge of the wireless link, which can be acquired through the Channel State Information (CSI). CSI represents the current condition of the channel, and consists of the attenuation and phase shift experienced by each spatial stream to each receive antenna in each of the OFDM subcarriers. CSI is provided in the 802.11n hardware by analyzing received packets using training sequences in the packet headers. For network algorithms such as rate selection, AP association, channel assignment, etc., to make a timely, optimal decision, accurate CSI estimates under various settings (e.g., different number of spatial streams, transmission antennas used, transmission powers, etc.) must be known. However, some of these settings might not have been sampled in recently received packets and additional frame transmissions are required to obt...