High-speed　train　communication　system　is　a　typical　high-mobility　wireless　communication　network.　Resource　allocation　problem　has　a　great　impact　on　the　system　performance.　However,　conventional　resource　allocation　approaches　in　cellular　network　cannot　be　directly　applied　to　this　kind　of　special　communication　environment.　A　multi-domain　resource　allocation　strategy　was　proposed　in　the　orthogonal　frequency-division　multiple　access　(OFDMA)　of　high-speed.　By　analyzing　the　effect　of　Doppler　shift,　sub-channels,　antennas,　time　slots　and　power　were　jointly　considered　to　maximize　the　energy　efficiency　under　the　constraint　of　total　transmission　power.　For　the　purpose　of　reducing　the　computational　complexity,　noisy　chaotic　neural　network　algorithm　was　used　to　solve　the　above　optimization　problem.　Simulation　results　showed　that　the　proposed　resource　allocation　method　had　a　better　performance　than　the　traditional　strategy.　©　2014,　Tianjin　University　and　Springer-Verlag　Berlin　Heidelberg.