Testbed Data Sheet_IoT Based Climatological Prediction Model_Wajeeh Anwer

Prototype Climatological HVAC Web of Things Smart Prediction Testbed Analysis to save the scarcely available resources in terms of electric energy consumption as well as running cost of air conditioners in TIC Data Center environment using instantiated Hidden Markov Model (HMM) Scroll to the bottom to see a graph of what the states and transitions the model thinks are likely on each day. Those likely states and transitions can be used to reestimate the green probabilities (this is the "forward-backward" or Baum-Welch algorithm), increasing the likelihood of the training data. Scroll right to see the results of doing so, and scroll all the way right to see the results of doing so for 11 iterations to improve and maximize the probabilities by minimizing the perplexity. A model is good to the degree that it assigns relatively high probability, low preplexity and resultantly the high accuracy to the test data.