Fixes issue #1476
Alternative to PR #1487

Force the client to reload when the bridge that is handling the media goes down.
This mitigates issues seen on the bridge because of a client re-joining the call with the same endpointId, BWE issues, etc.
This behavior is configurable through 'enableForcedReload' setting in config.js.

If ICE fails will set the special request restart attribute
in the 'session-terminate' sent to Jicofo in order to restart
the Jingle session.

Simplifies the logic for delayed ICE failed event by relying
on XMPP ping instead of the networkInfo module to check
if the internet is online.

There's a plan for using ping to detect XMPP WebSocket
disconnected instead of waiting for timeouts on the network layer.

This also simplifies ICE failed handling logic.

Adds extra 15 seconds before emitting ICE failed event. If the OS is capable of
reporting internet offline status then will start counting when the internet
comes back online.

The reason for that is when ICE restarts are disabled a user will get the page reload
screen immediately, but there's a chance to recover as long as the channels have not
expired on the bridge.