Sender: Tony Li <tony1athome@gmail.com>
Content-Type: text/plain;
	charset=utf-8
Mime-Version: 1.0 (Mac OS X Mail 16.0 \(3826.700.81.1.4\))
From: Tony Li <tony.li@tony.li>
In-Reply-To: <CDB46701-00A9-4AB9-AB76-5B790255A5A7@gmail.com>
Date: Tue, 5 May 2026 11:20:09 -0700
Content-Transfer-Encoding: quoted-printable
Message-Id: <CC0D8A2E-8992-43FD-8604-E804C9F3780E@tony.li>
References: <m2fr4e7q54.fsf@ja.int.chopps.org>
 <5A480F13-60B5-4E5E-8D14-7EEDEE4389D6@gmail.com>
 <451DEFD1-9E1E-4F55-B351-351D3A3F1327@tony.li>
 <CDB46701-00A9-4AB9-AB76-5B790255A5A7@gmail.com>
To: Carlos Pignataro <cpignata@gmail.com>
Message-ID-Hash: AICI3GNQR6PO7BH3GX3TDMHDJGB6ZJSY
CC: Christian Hopps <chopps@chopps.org>, lsr <lsr@ietf.org>,
 =?utf-8?B?IuKAnGxzci1hZHNAaWV0Zi5vcmfigJ0i?= <lsr-ads@ietf.org>,
 ops-ads <ops-ads@ietf.org>, green@ietf.org
Precedence: list
Subject: =?utf-8?q?=5BGreen=5D_Re=3A_Next_steps_for_draft-many-lsr-power-group-02?=
Archived-At: 
 <https://mailarchive.ietf.org/arch/msg/green/ONkCmJOyfMdtAe2ope7OCWMg8d8>


Hi Carlos,

> The intent is simply to ensure that the evaluation captures the net =
system-level impact (i.e., whether the mechanisms enable sufficient =
consolidation to reduce overall energy consumption relative to a =
baseline.) In other words, the considering both sides: the additional =
overhead introduced, and the potential energy savings from traffic =
consolidation and resource idling. How is the simulation / premise / =
framework evaluating net >0 or <0?


Thank you for the clarification, but I still cannot answer.  It depends.

If the network is running at 98% of capacity throughout, then there is =
nothing that can be done.  No savings, so no benefit.

If the network is running at 10% of capacity, then it=E2=80=99s very =
likely that 70-80% of the network can be shut down (depending on the =
operator's redundancy requirements),

What we have seen is that our simulations have shown excellent benefits, =
but the exact number vary greatly, again depending on the traffic =
demand, topology, hardware, etc.

I get that you want an easy answer.  I=E2=80=99m sorry to say that as =
with many things in life, there is none.

This technology will help networks that have substantial variance in =
their traffic demand, and not at all with networks that run continually =
saturated.  And in between, it will give some benefit, but your mileage =
may vary. Whether it=E2=80=99s enough to matter depends on your personal =
situation and the price of power.

Tony