By Mary
BrainRank Machine learning. Google explains the machine like speech recognition (MI): a computer that analyzes large amounts of data to recognize patterns and “learn” from them. In a dynamic environment like Google’s data center, it can be difficult for humans to see how all of the variables—IT load, outside air temperature, and the link.—interact with each other.
One thing computers are good at is seeing the underlying story in the data, so the information we gather in Google daily operations and ran it through a model to help make sense of complex interactions that the team—being mere mortals—may not otherwise have noticed.
To keep the BrainRank machine, who wants to replace humans, running at its best. Google explains this simplified version of what the models do: take a couple of data, find the hidden interactions, then provide recommendations that optimize for efficiency.
Google PUE Optimization Application
- Straightforward application of ANN/supervised learning
– Lots more happening at Google (and FB, Baidu, NFLX, MSFT,AMZN,…)
Google Use case: Predicting Power Usage Effectiveness (PUE)
-Basically: They developed a neural network framework that learns from operational data and models plant performance
–The model is able to predict PUE2 within a range of 0.004 + 0.005 , or 0.4% error for a PUE of 1.1.
- “A simplified version of what the models do: take a bunch of data, find the hidden interactions, then provide recommendations that optimize for energy efficiency.”
–http://googleblog.blogspot.com/2014/05/better-data-centers-through-machine.html
Google Use Case: Features
- Number of features relatively small (n = 19)
Google Use Case: Algorithm
1.Randomly initialize the model parameters θ
2.Implement forward propagation
3.Compute the cost function J(θ)
4.Implement the back propagation algorithm
5.Repeat steps 2-4 until convergence
–or for the desired number of iterations
- Very standard…
Google Use Case: Details
- Neural Network
–5 hidden layers
–50 nodes per hidden layer
– 0.001 as the regularization parameter (λ)
- Training Dataset
–19 normalized input parameters (features) per normalized output variable (the DC PUE)
- Data normalized into the range [-1,-1]
– 184,435 time samples at 5 minute resolution
- O(2) years of data
–70% for training, 30% for cross validation
If you want to learn more about what is the new classical algorithm google search launched recently, please check this article: What is Google BrainRank?