Chances are your IT workloads will be greener.
And while information technology might not be the first thing you think of when you say the words “climate change”, technology’s role in greenhouse gas emissions keeps growing. grow. That means IT managers have work to do when it comes to sustainability.
Here, Matt Buchner, senior director of cloud solutions architecture at NTT Data Services, an IT service management company headquartered in Plano, Texas, discusses some green IT considerations and why it’s important to think about environmental costs of technology, even when delivered through the cloud.
How can CIOs and IT managers incorporate environmental sustainability into their operations?
Matt Bucher: Ideally, a sustainability initiative starts at the board and management level. Part of a company’s emissions comes from its IT workloads, so it is necessary to define an IT-specific plan.
The first step is to measure the amount of CO2 emitted by your IT workloads. This gives you a base to work from.
IT needs to develop a goal, a plan that can then be implemented to make IT workloads more sustainable. It takes work and effort to make IT more sustainable. It’s not magic.
So we need to think about all the benefits you can get from moving to green IT, and that’s more than just saving CO2.
For example, sustainability is a way to differentiate yourself from the competition. What we are currently seeing in the market is a big challenge in finding talent. You can use a good sustainability plan as a differentiator to attract talent to the organization.
There are many reasons to develop a plan and implement it, but the question then becomes: how do you do it? Moving to the cloud can be a good first step, as cloud providers tend to be more efficient with power management and cooling.
If you really want to optimize more, you need to modernize your apps. It takes more time and effort, but it is proportional to the benefits. For example, one aspect of a modernized application is scalability. Instead of running a set number of servers 24/7 regardless of the load, you can increase and decrease this number, change the server specifications as needed. And if you only activate the servers when you need them, like with a light, you reduce your emissions.
If you want extra gains, it’s all about making apps smaller. Suppose you are running an application which contains tons of software, which is very complex, which is always calculating and the CPU is getting hot, the fans are spinning very fast. If you can make that same app much smaller and lighter, that’s much greener. Container, serverless, and event-driven architectures have a much smaller footprint than traditional applications.
If you’re considering machine learning, there’s a whole other set of things to look at. Machine learning can use a lot of computing power to build models. Machine learning is fairly new, but there are other legacy ways to approach it and more modern and sustainable ways to do machine learning. You can reuse pre-trained models so you don’t have to recalculate from scratch each time. You can save a lot of time, energy and money by doing this.
What is a potentially overlooked aspect of setting green IT goals that CIOs and other IT managers should keep in mind?
Bucher: You might say, “I want to reduce my emissions by 50% within two years. But if in two years, your company has grown three times, your computing needs have increased considerably, and yet you must reduce your emissions. So it can be really difficult. A more achievable goal is to link emissions targets in proportion to company size.
The [overarching] objective is to achieve net zero emissions. But this will take time. If you look at cloud provider commitments, we’re looking at five to 10 years to be 100% green power. Additionally, results from S&P’s 2021 Global Corporate Sustainability Assessment (CSA) show that most companies have not even set their initial emissions reduction targets, let alone net zero targets. CSA found that only 23.7% of respondents have set a net zero emissions goal. The first step is to set these goals and make commitments within the organization to reduce emissions.
Sustainability is not just about CO2 but also about water use, for example, because a lot of water is used to cool data centers. If you look at the cloud providers’ sustainability pages, they discuss emissions, but they also set targets around water use, because data centers use billions of gallons of water.
How can IT teams start measuring their carbon emissions?
Bucher: If you use [a large cloud provider such as] AWS or Azure, then you can find a dashboard in the console that will show you how much CO2 you are emitting. If you don’t have this kind of dashboard, you can do the math to understand how much energy you’re consuming.
What about the organizations that are currently there?
Bucher: You may know how much energy you use in kilowatts because it’s part of your bill. And then you can use it to calculate your emissions.
Part of this is whether the electricity is produced by wind turbines, solar parks or nuclear power plants – and in such cases, there will be much less CO2. If the energy is generated by coal or gas power plants, there will be more CO2 generated. So you have to look at how this energy is produced for the locality.
Using cloud services does not eliminate environmental issues – for example, companies will always have legacy e-waste from the technology – and cloud computing comes with other environmental costs. What might be useful to consider about these questions?
Bucher: [Among its benefits], I think the cloud has the advantage of shared hardware. But I will say – as a counterpoint to my penchant for the cloud – that in the cloud things are so easy to consume. You can just click or sign in and boom, you are now using a lot of cloud resources.
In a data center, you can walk into the server room, you feel the heat, you hear the fans. Someone who has never walked into a data center can now run large computer servers. The use of technology is so abstract that we can forget what it takes to power it behind the scenes.
That’s our job in IT: to educate and make sure people are aware of and can make good use of the technology provided to them. Technology is made so easy that [its energy use] can be abused. But if we are monitoring, measuring and educating people about sustainability and technology issues, then we are in a better position.
In what ways can IT teams in particular begin to be more aware of their environmental footprint?
Bucher: Seeing how much energy you’re already consuming is one thing. The next level of green computing is to estimate the future consumption of a given application and choose accordingly. If you have two options that are similar in performance, but one is more environmentally friendly than the other, you can make a decision based on this information.
[If you’re using a cloud service], use automatic server shutdown. Some of the cloud computing services will have an automatic shutdown feature built in. For example, AWS Cloud9 is a service that, by default, automatically enters hibernation mode after 30 minutes of non-use. If you look at the servers you’re already using, there’s probably a lot that aren’t actually being used. You need to look into this, make sure the servers shut down [when not in use], so set up an auto intervention or shutdown option. It’s not always built-in, and you’ll have to implement and test it, but it can lead to a lot of cost and emissions savings.
When migrating to the cloud, it’s important to take a close look at the cloud region where your data is stored. Network emissions factors are an important part of the cloud’s carbon footprint. Grid emissions factors list the type of local energy sources cloud regions use to power their infrastructure, and each cloud region will have different levels of carbon emissions efficiency. Of course, other factors such as data location, latency, and price will also come into play, but choosing the most efficient region will have a significant impact on your workload’s overall emissions.
This interview has been edited for length and clarity.