New challenging deployment scenarios are accommodating portable devices with limited and heterogeneous capabilities that roam among wireless access localities during service provisioning. That calls for novel middlewares to support different forms of mobility and connectivity in wired-wireless integrated networks, to provide runtime service personalization based on client characteristics, preferences, and location, and to maintain service continuity notwithstanding temporary disconnections due to handoff. The paper focuses on how to predict client horizontal handoff between IEEE 802.11 cells in a portable way, only by exploiting RSSI monitoring and with no need of external global positioning, and exploits mobility prediction to preserve audio/video streaming continuity. In particular, handoff prediction permits to dynamically and proactively adapt the size of client-side buffers to avoid streaming interruptions with minimum usage of portable device memory. Experimental results show that our prediction-based adaptive buffering outperforms traditional static solutions by significantly reducing the buffer size required for streaming continuity and by imposing a very limited overhead.