How Has Google Improved Its Data Center Management Through Artificial Intelligence


Historically, the staff at data centers adjusted the settings of the cooling systems to save energy costs. Times have changed, and this is the sweet age of AI where intelligent systems are on guard 24/7 and automatically adjust these settings to save costs.

Last year, a tornado watch prompted Google’s AI system to take control of its cooling plant in a data center and it modified the system settings. The staff at Google was initially perplexed because the changes did not make sense at the time. However, after a closer inspection, the AI system was found to be taking a course of action that reduced the energy consumption.

The increase and decrease in temperature, humidity levels, and atmospheric pressure force the change in weather conditions, and they can stir a storm. This weather data is used by Google’s AI to adjust the cooling system accordingly.

Joe Kava, Google’s Vice President of data centers, revealed Google’s use of AI for data centers back in 2014. At that time, Kava explained that the company designed a neural network to assess the data which is collected from its data centers and suggested a few strategies to enhance its processing. These suggestions were later utilized as a recommendation engine.

Kava explained that they had a single solution which would provide them with recommendations and suggestions. Afterward, the qualified staff at Google would begin modifying the pumps, heat exchangers, and chillers settings according to the results of AI-based recommendations. In the last four years, Google’s AI usage has evolved beyond Kava’s proposed vision.

Presently, Google is adopting a more aggressive approach. Instead of only dishing out recommendations to the human operators could act on them, the new system would itself go onto adjust the cooling settings. Jim Gao, a data engineer at Google, said that the previous system saved 20 percent energy costs and that the newer update would save up to 40 percent in energy consumption.

Little Adjustments

The tornado watch is only a single real-world instance of Google’s powerful AI and its impact on energy savings to an extent which was impossible with manual processes. While at first glance, the minor adjustments done by the AI-enabled system might not seem enough. However, the sum of each savings results in a huge total.

Kava explains that the detailing performed by the AI systems makes it matchless. For instance, if the temperature in the surroundings of the data center goes from 60 degrees Fahrenheit to 64 degree Fahrenheit while the wet-bulb temperature is unaffected, then an individual from the data center staff would not go think much about updating the settings of the cooling system. However, the AI-based system is not so negligent. Whether there is a difference of 4 degrees or 40 degrees, it keeps on going.

One interesting observation regarding the system was its noticeably improved performance during the launch of new data centers. Generally, new data centers are not efficient as they are unable to get the most of the available capacity.

From Semi to Full Automation

The transfer of critical tasks of the infrastructure to the AI system has its own implications and considerations.

With the increase of data and runtime, the AI system becomes more and more powerful and therefore, management also starts to have faith in the system, enough to give it some control. Kava explained that after some experimentation and results, slowly and gradually the semi-automated tools and equipment are replaced by fully automated tools and equipment.

Uniformity is the key to Google’s AI exploits; it is not possible to implement AI at such a massive scale without uniformity. All the data centers are designed to be distinct such that a single AI system is not possible to be integrated across all of them at the same time.

The cooling system of all the data centers are constructed for maximum optimization according to their geographical locations. Google has tasked its data engineering team to continuously look for any possible techniques for energy savings.

Additionally, ML-based models are trained according to their sites. The models have to be programmed to follow that site’s architecture. This process takes some time. However, Google is positive that this consumption of time would result in better results in the future.

The Fear of Automation

One major discussion point with this rapid AI automation and similar AI-based ventures is the future of “humans” or the replacement of the humans. Are the data center engineers from Google going to lose their jobs? This question contains one of mankind’s biggest fears regarding AI. As AI progresses, this uncertainty has crept into the minds of workers. However, Kava is not worried. Kava stated that Google still has staff at its disposal at data centers that is responsible for maintenance. While AI may have replaced some of their “chores”, the staff still has to perform corrective repairs and preventative maintenance.

Kava also shed some light on some of AI’s weaknesses. For instance, he explained that whenever the AI system finds itself in the midst of uncharted territory, it struggles to choose the best course of action. Therefore, it is unable to mimic the brilliance of humans in making astute observations. Kava concluded that it is recommended to use AI for cooling and other data center related tasks, though he cautioned that there must be some “human” presence to ensure that nothing goes amiss.

Final Thoughts

Google’s vision, planning, and execution of AI in its data centers are promising for other industries too. Gao’s model is believed to be applicable to manufacturing plants that also have similar setups like cooling and heating systems. Similarly, a chemical plant could also take advantage of AI and likewise, a petroleum refinery may use AI in the same way. The actual realization is that, in the end, such AI-based systems can be adopted by other companies to enhance their systems.

What Is Artificial Neural Network and How Does It Work?


The whole idea behind artificial intelligence is to make a machine act like a human being. While many sub-divisions of AI originated with their own set of algorithms to mimic humans, artificial neural networks (ANNs) are AI at its purest sense; they mimic the working of the human brain, the core and complex foundation which influences and affects the thinking and reasoning of human beings.

What Is an Artificial Neural Network?

ANN is a machine learning algorithm. It is founded on the scientific knowledge about organic neural networks (working of the human brain). ANN works quite similar to how human beings analyze and review information. It is composed of several processing units which are linked together and perform parallel processing for the computation of data.

As machine learning is primarily focused on “learning,” ANNs continuously learn and adapt. The processing units in ANNs are commonly referred to as neurons or nodes. Bear in mind that neuron in biology refers to the most basic units in the human nervous system. Each node is linked via arcs which have their own weight. The artificial neural network is made up of three layers.

Input

The input layer is responsible for accepting explanatory attribute values which are collected from observations. Generally, input nodes are explanatory variables. Patterns are submitted to the network by the input layer. Subsequently, those patterns are then analyzed by the hidden layers. The input layer nodes are not involved in modifying any data. They accept individual values as inputs and then perform duplication of the value so it can be passed on to multiple outputs.

Hidden

The hidden layers modify and transform values collected from the input layer. By utilizing a technique of weight links or connections, the hidden layer initiates computation on the data. The number of hidden layers depends upon the artificial neural network; there may be one or more than one hidden layers. Nodes in this layer multiply the collected values by the weights. Weights are a predetermined set of numbers which convert the input values with the help of summation to generate an output in the form of a number.

Output

Afterward, the hidden layers are connected to an output layer which may also receive a connection directly from an input layer. It generates a result, which is associated with the response variable’s prediction. Generally, when the machine learning process is geared towards classification and its disciplines, there is a single output node. The collected data in the layer is integrated and modified for the generation of new values.

The structure of a neural network is also called topology or architecture. All the above layers of the ANN form the structure. The planned design of the structure bears utmost importance to the final findings of the ANN. At its most basic, a structure is divided into two layers which are comprised of one unit each.

The output unit also possesses two functions: combination and transfer. When there are multiple output units, then logistic or linear regression can be at work and the nature of the function ultimately decides it. ANN’s weights are actually coefficients (regression).

So what do the hidden layers do? Well, the hidden layers are incorporated into ANNs to enhance the prediction strength. However, it is recommended to add them smartly because excessive use of these layers may mean that the neural network stores all the learning data and may not able to generalize, causing an over-fitting problem. Over-fitting arises when the neural network is not able to discover patterns and is heavily reliant on its learning set to function.

ai1

 

Applications

Due to their accurate predictions, ANNs have broad adoption across multiple industries.

Marketing

Modern marketing focuses on segmenting customers within well-defined and distinct groups. Each of these groups exhibits certain characters that are reflecting of its customer habits. In order to generate such segmentation, neural networks present themselves as an efficient solution for predicting strength to identify patterns in a customer’s purchasing habits.

For instance, it can analyze how much time customers take between each purchase, how much do they spend, and what do they mostly purchase. ANN’s input layer takes all the attributes like location, demographics, and other personal or financial information about a customer to generate meaningful output.

Supervised neural networks are usually trained to comprehend the link between clusters of data. On the other hand, unsupervised neural networks are used for segmentation of customers.

Forecasting

Forecasting is a part and parcel of a varied list of domains including governments, sales, finance, and other industries, especially their use in the monetary and economic aspects. Often, forecasting faces a tumbling roadblock because of its complexity. For instance, the prediction of stocks is considered difficult because the stock market addresses multiple seen and unseen factors where traditional forecasting becomes ineffective.

This conventional forecasting is founded merely on statistics. ANNs use the same statistical methods and techniques and enhances forecasting where its layers are sophisticated enough to tackle the complexity of the stock market. Moreover, in contrast to the conventional methods, ANN is non-restrictive for input values and residual distributions.

Image Processing

Since the layers in artificial neural networks are able to accept several input values and compute them flexibly to determine complex and non-linear hidden relationships, they are well-equipped to serve in image processing and character recognition. In criminal proceedings like bank frauds, fraud detection requires accurate results for character recognition because humans cannot go over thousands of samples to pinpoint a match. Here, ANNs are useful as they are able to recognize the smallest of irregularities. Similarly, ANN is used in facial recognition with positive results where they are able to improve governance and security.

Final Thoughts

The emergence of artificial neural networks has opened a whole new world of possibilities for machine learning. With their adoption in real-world industries, the algorithm has become one of the most trending and research topics in a short period of time.