If you measure wind speeds throughout a year, you will notice that in most areas strong gale force winds are rare, while moderate and fresh winds are quite common.
The wind variation for a typical site is usually described using the so-called Weibull distribution, as shown in the image.  (More information)

This shows the frequency of varying wind speeds during December when we most need supplementary power. This particular site has a median wind speed of 4.9 mph. Which is not very good!

In practical terms this means  the investment in a wind turbine would not pay back and the money would be better spent on additional solar panels.

An alternate way to interpret the data is to view how many days of power generation one would get with turbines of different cut-in speeds (the speed at which the turbine starts generating power). These figures are shown to the right. Most turbines cut in at 12-15 mph. With these we might see one day of power generation. Some models claim to cut-in at 8 mph and at these speed we would still only get 5 days.

There are some companies trying to produce turbines that operate at lower speeds but most are in the experimental stage and power generation curves are hard to find. We will be keeping and eye on these technologies.  However the power in wind is proportional to the velocity cubed. So wind at 10mph has 8 times the power of wind at 5mph. Bottom line, there's no substitution for wind speed.  On the micro technology front MotorWind has mini turbines. (See video)

Another area being pursued is the 10kW Magnetically Levitated Vertical Axis Wind Turbine VAWT. This uses a rotor which floats on a magnetic cushion to reduce fiction. (See video)