Eclipse Authors: Pat Romanski, Elizabeth White, Liz McMillan, David H Deans, JP Morgenthal

Related Topics: @CloudExpo, Eclipse

@CloudExpo: Article

Iron, Power, and Cloud Computing: Let's Get Real

The World Needs Two Terawatts of Electricity. Cloud Can Help Moderate That

I'm the least sure of opinions that people are most sure of.

And I'm supposed to be writing about Cloud Computing, not geopolitical debate.

Whether we like it or not, these two things are intertwined, because the fundamental underlying all things Cloud is energy: its use, its price, and the competition for it. Most people have very strong opinions about energy--how we produce it and use it--and in my opinion, those opinions often cloud the debate.

If you hate coal or nuclear power, you really hate them. If you are contemptuous of wind and solar, you are really contemptuous of them. But let's pretend we are the hypothetical Martians of old, and gaze down on Planet Earth to examine its needs dispassionately.

Green Is In
Cloud Computing is Green Computing. Anything beyond that statement dumps us quickly into numerous debates, oftentimes personal and nasty ones. The idea that there is ongoing, dangerous, human-induced Global Warming is widely accepted, yet also used as a rhetorical football. A report earlier in the year by Greenpeace, for example, seemed to take opportunistic umbrage against specific high-profile companies that chose to use traditional power sources for their new server farms.

Whether you believe Global Warming is going to cause our grandchildren to suffer greatly, or is a global hoax, or something in between, you'd agree that we should keep trying to be more efficient about energy use, right? Whether you think wind and solar power should be our priorities, or are a fan of nuclear power, or think our fossil-fuel dependence is simply a hard fact of life, you'd like to see us use less of all of it, right?

So although I don't think that all recent Cloud Computing announcements represent Cloud Computing truly--a private, on-site data center isn't necessarily virtualized, doesn't necessarily deliver services, and surely is no more elastic (provisioning promises aside) than whatever was there before--I am in favor of their uniform emphasis on lower energy consumption per unit, whatever that unit of measurement may be.

It wasn't long ago that Green Computing was not part of any conversation. To be sure, there were concerns about monitor radiation, and disgust that the West was sending old systems to developing nations so that very poorly paid laborers could bust them up and be directly exposed to the poisons within. This disposal issue has not gone away. But today, Green is meant to refer to energy usage, to reducing carbon footprints (even if you have to charter a jet to Bali to make your point), to keep us from unwittingly turning the Earth into Venus.

I was first made aware of what we know think of Green Computing only five years ago, when I interviewed Dr. David Yen (then with Sun Microsystems) about the new Sun Niagara servers, at a conference in New York City. Since that time, all-resource virtualization has entered IT discussions in a big way. It now seems obvious to virtualize always, make those systems more efficient, and look at hardware that's explicitly engineered to run cooler when it's time to buy again.

Fun With Numbers - Demand Side
Here is where it's useful to dispense with rhetoric and have some fun with numbers. I'll try to keep everyone awake in this part of the article.

I'm going to take a look at power consumption on a big scale, by the numbers. Note: I'm measuring this by the watt rather than the watt-hour. Multiply the numbers by 8,760 (the number of hours in a year) to get watt-hours.

I'm also using rounded numbers from a few sources, without an engineer's precision. However, I am confident that these numbers paint an accurate picture of the dimension of the challenge we face.

* Let's start with a local benchmark, so that we can understand the global scale later on: A recent heat wave brought the afternoon high to 113 degrees in downtown Los Angeles. The metro area needed 48,000 megawatts of power to keep the lights on.

* We earthlings use a collective 2 terawatts of electricity (more or less), or 2 million megawatts. This is continuous, average usage, around the clock. Spikes are higher, although alleviated somewhat by the fact of the sun moving across the sky, keeping half of us (more or less) in the dark at any particular time.

* The US uses slightly less than a quarter of these 2 terawatts--slightly under 500 gigawatts, or 500,000 megawatts.

* Divide this number by the US population to find that the country needs slightly more than 1,500 watts per person, 24/7/365.

* Canada uses more power per person than this, closer to 2,000 watts. (it's cold up there and there's a lot of heavy industry.) Scandinavia and Finland have the same problem, with similar consumption.

* Germany comes in at a little more than 800 watts per person. The EU average is around 700.

* Mexico comes in at slightly less than 200. It's in the same neighborhood as Turkey and Brazil.

* Then there's China at 277..and India at around 50.

The outline and dimensions of the problem start to emerge. You think China and India are seriously trying to get their hands on every source of energy now, well, just wait. These two countries, with one-third of the world's population, still lag the world average, and India severely so.

It's no surprise to learn further that there are many more countries below the world average than above it. In a converse corollary to Garrison Keillor's dictum about Lake Wobegon, most of the world's economies are below average.

Fun With Numbers - Supply Side
A big power plant, whether nuclear or fed by fossil fuel, will produce between 1,000 to 2,000 megawatts.

* Wind and solar farms just can't match that today. Who knows when they will? The massive, well-known windfarm complex in the Altamont Pass on the edge of the San Francisco Bay Area, for example, now has around 5,000 wind turbines and generates an average of around 125 megawatts. It also kills thousands of birds every year, including more than 1,000 raptors.

This last statement is not meant to be hard on the wind farms. One "little" accident at a nuke plant can ruin everyone's day, as we know. And you probably don't really want to see the several daily coal trains, or massive ships, storage tanks, and pipelines that feed fossil-fuel plants.

The point is, we are nowhere near figuring out a way to meet our power needs with grace, elegance, and natural beauty. We are also nowhere near either reaching peak demand or the global chaos that will result if we can't.

All is not lost, however. That 2 terawatts of power requires two thousand plants that can each produce 1,000 megawatts. To increase this by a full 50% would cost $3-5 trillion dollars, a number that can boggle the mind until one remembers that the US recently got into trillion-dollar territory just to bail out Wall Street and other miscreants. The EU is flirting with this number in solving its own financial problems as well.

And the world power supply is not going to go up 50% anytime soon. A 10% increase would run $300 to $500 billion, for example.

Furthermore, the 2 terawatts is just a fraction of global power consumption, which comes in at  15 terawatts. To start with, we have a lot of cars and trucks. Trains, planes, and really big ships. It also requires about 3 terawatts of resources to produce that 2 terawatts of electricity.

Simply viewed and stated, these numbers show that it behooves all of us to seek energy efficiency. Rather than make a political football of global warming, we should just work to make things better now. Man plans, Buddha laughs, and a single volcanic eruption could bring on a long winter that would easily trump our pitiful efforts to destroy things.

I found it bizarrely ironic to see many global financial advisors in a panic when energy consumption dropped in the wake of the Great Recession. The panic was not over a negative global growth rate, it was over the fate of the energy industry if we stop using less of everything. We should continue to do so.

The Real Fun: Per-Person Productivity
It is here that efficiency again raise its head. Let's look again at per-capita power consumption, and match it up against per-capita production. The US, for example, produces about $45,000 in GDP per capita (ie, per person). Each of these people consumes about 1,500 continuous watts, or 1.5 kilowatts. So, fourth-grade math shows that US productivity is about $30,000 per kilowatt per person of power consumption.

The EU as a whole produces $32,500 GDP with its 0.7-kilowatt/per person average, or about $46,000 in productivity per kilowatt of consumption. In other words, the EU is more productive than US, which must come as a great shock to Americans. (Let's not forget that the US has a much more extreme climate. This probably accounts for the difference and then some.)

China has a $3,700 GDP (not adjusted for local prices), and uses about 0.3 kilowatts per person. Thus, its productivity comes in at about $13,000 per kilowatt per person of consumption. This is a bit more than 40% of US levels, in a country of similar size and climate.

Also contrast this with Japan, which produces about $40,000 in GDP, with 868 continuous watts per capita in consumption. Japan thus produces about $46,000 per kilowatt per person, equal to the EU. China has recently surpassed Japan as having the world's second-largest overall economy; it still has a long way to go to catch its neighbor's productivity.

India, for all of its touted economic progress, still has a per capita GDP of around $1,000. It ranks in the bottom quartile of relative wealth in the world. Match its GDP with its consumption of 50 watts per person, however, and you get $20,000 in productivity per kilowatt, more than 50% higher than China!

In my resident country of the Philippines, these numbers are $1,700 GDP and about 64 watts per person. The productivity number is thus about $28,000 per kilowatt consumed. Eat my dust, India! Even when one considers that 13% of this economy comes from overseas remittances, it's an astonishing number.

It's also a number that could make it appear that the Philippines is doing just fine; in some respects yes, but in many respects no. It remains a country that announces itself as a developing country the instant you get off the plane. India does as well, but not China, at least in its major cities. Unfortunately, the US seems increasingly to do so many of its crustier cities.

Energy Intensity
This last little round of calculations led me to blunder into the concept of energy intensity. The concept defines how much GDP is generated per million BTUs consumed, similar to my little exercise above. It groups countries by efficiency along the X-axis, and wealth along the Y-axis.

Each country is unique, so I don't see hard-and-fast lessons to be drawn from this chart. Ideally, we would want everybody in the upper right-hand corner, where no one is now. Hong Kong comes closest, but if there was ever a special case, it would be Hong Kong (small, urban, completely export driven, OK climate, not a truly independent country).

The closest independent countries to Hong Kong are Austria and Switzerland. Not everyone can be Austria or Switzerland, either; nor would everyone want to be, nor would these countries want everyone to be.

Back to the Cloud
This brings me back to the idea that IT will continue to be the greatest efficiency enabler we have, and Cloud Computing is the most efficient form of IT. I was ranting a few days ago that private cloud is a flawed concept, and hybrid cloud is meaningless. I don't like the FUD being thrown out there, because I think it creates straw men and false debates, and impedes progress.

To me, the true promise of Cloud lies in its metered service dimension, and in the shift in capital expenditure burden from users to providers.

I remain convinced that the big distinction we should make about Cloud is whether it is handling internal data, B2B data, or consumer data. I also remain convinced that the starting point with Cloud is to ask, "what do I want to do?"

But yet, the big vendors of private cloud are on the right track by emphasizing lower power consumption and virtualized performance.

Iron and Power
Someone still must, and should, buy a lot of iron. And we will need a lot of power to run this stuff. Worldwide power consumption represents a mammoth challenge, but it is not a problem. Violence is a problem. Water pollution is a problem. Disease is a problem. The number of people on the planet may be a problem.

But delivering power is a challenge, not a problem. Ask the Geico guys; they clearly have embraced the non-caveman lifestyle and seem to prefer it.

The question is whether it is possible to build the power plants we need within a spirit of fair debate. Namecalling and euphemistic PR spinning really does nothing to accomplish the goal, and the goal is to continue to improve lives. My experience in living in a developing country tells me that not everyone wants to live like God in France; most of just want their lives to be a little less of a struggle.

As the efficiencies of design-with-a-purpose, virtualization, and old-fashioned economies of scale kick in, we can, as a people, moderate total power consumption while raising productivity. It's not realistic to imagine a gross conversion to solar and wind power, or to nuclear power just yet. We have to burn some coal, we have to burn some oil, and we have to burn some natural gas. It's not pretty, but there's no getting around it. Cloud computing efficiencies will make it as pretty as possible, if not as pretty as the billowing clouds in the springtime sky.

More Stories By Roger Strukhoff

Roger Strukhoff (@IoT2040) is Executive Director of the Tau Institute for Global ICT Research, with offices in Illinois and Manila. He is Conference Chair of @CloudExpo & @ThingsExpo, and Editor of SYS-CON Media's CloudComputing BigData & IoT Journals. He holds a BA from Knox College & conducted MBA studies at CSU-East Bay.

IoT & Smart Cities Stories
In his general session at 19th Cloud Expo, Manish Dixit, VP of Product and Engineering at Dice, discussed how Dice leverages data insights and tools to help both tech professionals and recruiters better understand how skills relate to each other and which skills are in high demand using interactive visualizations and salary indicator tools to maximize earning potential. Manish Dixit is VP of Product and Engineering at Dice. As the leader of the Product, Engineering and Data Sciences team at D...
When talking IoT we often focus on the devices, the sensors, the hardware itself. The new smart appliances, the new smart or self-driving cars (which are amalgamations of many ‘things'). When we are looking at the world of IoT, we should take a step back, look at the big picture. What value are these devices providing. IoT is not about the devices, its about the data consumed and generated. The devices are tools, mechanisms, conduits. This paper discusses the considerations when dealing with the...
Bill Schmarzo, Tech Chair of "Big Data | Analytics" of upcoming CloudEXPO | DXWorldEXPO New York (November 12-13, 2018, New York City) today announced the outline and schedule of the track. "The track has been designed in experience/degree order," said Schmarzo. "So, that folks who attend the entire track can leave the conference with some of the skills necessary to get their work done when they get back to their offices. It actually ties back to some work that I'm doing at the University of San...
Bill Schmarzo, author of "Big Data: Understanding How Data Powers Big Business" and "Big Data MBA: Driving Business Strategies with Data Science," is responsible for setting the strategy and defining the Big Data service offerings and capabilities for EMC Global Services Big Data Practice. As the CTO for the Big Data Practice, he is responsible for working with organizations to help them identify where and how to start their big data journeys. He's written several white papers, is an avid blogge...
Dynatrace is an application performance management software company with products for the information technology departments and digital business owners of medium and large businesses. Building the Future of Monitoring with Artificial Intelligence. Today we can collect lots and lots of performance data. We build beautiful dashboards and even have fancy query languages to access and transform the data. Still performance data is a secret language only a couple of people understand. The more busine...
If a machine can invent, does this mean the end of the patent system as we know it? The patent system, both in the US and Europe, allows companies to protect their inventions and helps foster innovation. However, Artificial Intelligence (AI) could be set to disrupt the patent system as we know it. This talk will examine how AI may change the patent landscape in the years to come. Furthermore, ways in which companies can best protect their AI related inventions will be examined from both a US and...
Enterprises have taken advantage of IoT to achieve important revenue and cost advantages. What is less apparent is how incumbent enterprises operating at scale have, following success with IoT, built analytic, operations management and software development capabilities - ranging from autonomous vehicles to manageable robotics installations. They have embraced these capabilities as if they were Silicon Valley startups.
Chris Matthieu is the President & CEO of Computes, inc. He brings 30 years of experience in development and launches of disruptive technologies to create new market opportunities as well as enhance enterprise product portfolios with emerging technologies. His most recent venture was Octoblu, a cross-protocol Internet of Things (IoT) mesh network platform, acquired by Citrix. Prior to co-founding Octoblu, Chris was founder of Nodester, an open-source Node.JS PaaS which was acquired by AppFog and ...
The deluge of IoT sensor data collected from connected devices and the powerful AI required to make that data actionable are giving rise to a hybrid ecosystem in which cloud, on-prem and edge processes become interweaved. Attendees will learn how emerging composable infrastructure solutions deliver the adaptive architecture needed to manage this new data reality. Machine learning algorithms can better anticipate data storms and automate resources to support surges, including fully scalable GPU-c...
Cloud-enabled transformation has evolved from cost saving measure to business innovation strategy -- one that combines the cloud with cognitive capabilities to drive market disruption. Learn how you can achieve the insight and agility you need to gain a competitive advantage. Industry-acclaimed CTO and cloud expert, Shankar Kalyana presents. Only the most exceptional IBMers are appointed with the rare distinction of IBM Fellow, the highest technical honor in the company. Shankar has also receive...