Phase‑sensitive optical time domain reflectometry （φ‑OTDR） combined with existing communication optical fibers in optical fiber composite overhead ground wires （OPGW） captures fiber vibrations caused by wind‑induced movement along overhead transmission lines. However， the mapping law between vibration signals and actual wind speeds is difficult to establish and traditionally relies on manual judgment.To address this issue， the random forest algorithm was introduced into the data analysis for distributed optical fiber wind speed monitoring. A three‑month field test was conducted on a 220 kV line with a total length of approximately 44.16 kilometers， and the experimental results showed that the proposed solution could predict wind speed in real‑time and evaluate its impact on overhead transmission lines in a distributed manner. This method could assist in evaluating potential risks brought by wind loads and guide subsequent operation， maintenance， and upgrade to ensure the safe and reliable operation of overhead transmission lines.