Solutions which require the internet's infrastructure to be replaced (all the routers and switches and so forth) have been proposed for many years, and never go anywhere. The only one I'm aware of is IPv6, and look how slowly that beast has taken off. That said, TCP sawtooth isn't as bad as you make it out to be - in most cases. Whenever a packet is dropped, the TCP connection drops its speed to around half, then gradually ramps up to where it was previously. You don't get 100% of your bandwidth utilization, but you do get to automatically adjust to changing network conditions. And as the number of TCP connections over one pipe increases, you get closer and closer to max utilization rates.
TCP fails when:
-competing against UDP, which has no congestion control and will clog a line even if every UDP packet is dropped
-there is interference in the line causing packet corruption, which TCP interprets as congestion
-competing against Microsoft products, which have TCP stacks that are tweaked to grab more than their fair share of the bandwidth
My understanding is that TCP congestion control generally isn't applied to backbones - I believe that ISPs throttle your traffic before sending it over an optic link so as not to overbook its capacity. You're probably just competing with your household, and possibly people on your block - can someone verify this?