ActiveCluster

I know there is from the array itself. I would also ask about replication bandwidth, but since you don't have access to the array....

Our storage team is blaming the replication network, but the load is so high there isn't even a load metric that shows a value for 15 minutes. These are the closest points that actually show a value

That's a fairly busy array. I've seen AC take some latency hits when it's busy. Nothing too severe. Couple of ms added to usually mirrored writes. We were able to shed some load by reducing snapshot frequency and retention.

My storage team is trying to blame the replication network even though Pure1 says we need a bigger controller

Always easy to blame the network. What's the pipe size and latency? Controller model? I would guess that it could use a bigger controller, but if there's some other way you could shed workload, that'd help, too.

Replication appears to be via 25 Gb ethernet with dedicated switches between data centers and 100 Gb uplinks controller is X70R3

I only have access to Pure 1, but is there a way to see the bandwidth utilization of the port on the array itself?

or from the vCenter plugin

I know you're dealing with AC issues, but I would check around AC. How many snaps are you keeping? Number of snapshots can drive higher load, which can negatively affect AC replication. Are you doing any async replication? Larger PGs can take longer to replicate, which can lead to issues that could affect AC. How many IOPS are you typically pushing? Maybe the array is just that busy servicing front-end IO and other services are suffering. Same goes for IOP size. Larger sizes means more buffering, which can affect latency, which can cascade to AC performance problems.

How many interfaces do you have connecting to your storage fabric. More interfaces means more queues, which can help push things through faster, but might negatively affect replication.