One of the main improvements in the IoT AggreGate Platform 5.5 release was machine learning, which gave data processing professionals a chance to extract required knowledge while analyzing time series streams and large data sets.
And more recently, we have added several algorithms allowing you to create trainable units with an option of online learning.
Such trainable units have two important features. The first is ability to train on a data set that is too large to fit into memory. The second is ability to update with new data that wasn’t available during initial learning.
In other words, a trainable unit can be trained on available data, used for predictions, and get updated as soon as new data arrives, which will improve the quality of further predictions.
Importantly, the trainable unit in this case is not trained from scratch, but updated, modifying its existing state with new training data set.
The plus point is that it takes significantly less time to complete online learning than would be needed for learning from scratch.
AggreGate IoT Platform is the solution primarily suitable for industrial automation, large enterprise and datacenter network monitoring and control. Nevertheless, people from different countries are eager to buy our IoT solution for their house or office digitalization.
This time, the license goes to Sweden to make one more house smarter and more comfortable.
Our customer purchased two TPP2 generation 2 boards with enclosures, one board with a display and the other one without a display. He equipped them with the GA1000 Wi-Fi module and purchased plenty of Tibbits to do experiments and learn how to use them.
One of the TPP2 units was sitting on his desk as a "lab-unit" where he developed and tested different solutions in Tibbo Basic, for instance, RTD with PT500 and PT1000 sensors, digital outputs controlled by time schedules, agent connection to the free AggreGate SCADA/HMI to name a few.
He did some experiments with Modbus frames from the RS485-port (Tibbit #05) to a Modbus simulator on his PC with good results. This was hopefully something he could use later on to get data from electricity meters, and eventually other Modbus compatible devices.
The second TPP2 unit was installed in customer’s garage where he connected two PT500 temperature sensors, one measuring the temperature in the garage and the other one measuring the outdoor temperature. It was possible to use it to control the temperature in the garage later on with a set point switching the electric heaters on and off.
The unit also downloaded correct time from internet time-servers via NTP and sunrise/sunset time for the customer’s location in northern Sweden from a website which provided the service. He used the sunrise/sunset time combined with a time schedule to control a digital output which turned the outdoor illumination on and off instead of using an outdoor light sensor.
Our customer also used another digital output with time schedule to control an electrical outlet for his car engine heater, so then he could switch it on and off from AggreGate without leaving the house.
The unit was also equipped with the barometric pressure sensor (Tibbit #35). The customer used the historic logging feature in AggreGate to store both temperature and barometric pressure data displayed on a dashboard.
He also started to develop a PI-controller which he intended to use in the other TPP2 unit to control the heating system of his house, with outdoor compensated flow temperature for the radiators, time schedules for energy-saving during the night and when the house was empty, automatic pump switch-off when heating was not needed. Right now it's controlled by a simple Danfoss regulator.