Local Computing Cloud That is Interactive With a Public Computing Cloud

Abstract

A home computing cloud (HCC) supports one or more Internet of Things (IoT) devices, possibly with different connectively protocols, in a local environment. The HCC often reduces the amount of data traffic sent to a public computing cloud (PCC) by locally processing collected device data rather than by sending the device data to the PCC for processing. This approach reduces the amount of data traffic sent over the network, improves data privacy and helps to maintain a desired quality of service level. In order to do so, the HCC may download an appropriate data analytic model from the PCC, train the model, execute the trained model to obtain prediction information from collected IoT device data, and upload the trained model to the PCC. Alternatively, the HCC and PCC may execute sub-models of the analytic model and exchange the outputs of the sub-models with each other.

1 . A method for supporting a home computing system, the method comprising:
 obtaining, by the home computing system, device data from at least one Internet of Things (IoT) device configured at the home computing system;   streaming, by the home computing system, the device data to a public computing cloud;   providing, by the public computing cloud, the device data to a data analytic model that the public computing cloud is executing for the home computing system;   in response to the providing, obtaining, by the public computing cloud, a first predictive result;   in response to the streaming, receiving, by the home computing system, the first predictive result from public computing cloud;   applying, by the home computing system, the first predictive result to the at least one IoT device;   determining, by the home computing system, an error measure based on the first predictive result and corrections information to the first predictive result;   when the error measure exceeds a predetermined threshold, sending, by the home computing system, the corrections information to the public computing cloud;   performing, by the public computing cloud, reinforcement learning based on received corrections information to obtain updated model parameters; and   applying, by the public computing cloud, the updated model parameters to the data analytic model.   
     
     
         2 . The method of  claim 1  comprising:
 in response to the sending the corrections information, continue streaming, by the home computing system, the device data to the public computing cloud; 
 in response to the continued streaming, receiving, by the home computing system, a second predictive result from the public computing cloud; and 
 applying the second predictive result to the at least one IoT device. 
 
     
     
         3 . A method for supporting a home computing system, the method comprising:
 identifying a data analytic model for the home computing system, wherein the home computing system supports at least one Internet of Things (IoT) device, wherein the data analytic model comprises a set of layers;   partitioning the data analytic model into a plurality of sub-models, wherein each sub-model comprises a different subset of layers of the data analytic model and wherein the plurality of sub-models comprises first sub-model and a second sub-model;   executing, by the home computing system, the first sub-model; and   executing, by a public computing cloud, the second sub-model.   
     
     
         4 . The method of  claim 3 , wherein the first sub-model comprises an input processing layer and the second sub-model comprises all hidden layers and an output layer. 
     
     
         5 . The method of  claim 3 , wherein the plurality of sub-models further comprises a third sub-model, the method comprising:
 executing, by the home computing system, a third sub-model, wherein the first sub-model comprises an input layer, the second sub-model comprises all hidden layers, and the third sub-model comprises an output layer.   
     
     
         6 . The method of  claim 3 , wherein the plurality of sub-models further comprises a third sub-model, the method further comprising:
 executing, by the home computing system, the third sub-model.   
     
     
         7 . The method of  claim 6 , wherein the first sub-model comprises an input processing layer, the second sub-model comprises all hidden layers, and the third sub-model comprises an output layer. 
     
     
         8 . The method of  claim 3 , the method further comprising:
 executing, by the home computing system the first sub-model until a predetermined layer of the data analytic model is reached;   sending, by the home computing system to the public computing cloud, output data from the predetermined layer; and   executing, by the public computing cloud, remaining layers of the data analytic model based on the output data received from the home computing system.   
     
     
         9 . The method of  claim 8 , wherein the output data is unrelated to source data from the at least one IoT device. 
     
     
         10 . The method of  claim 8 , the method further comprising:
 determining a predetermined amount of generated traffic data between the home computing system and the public computing cloud;   executing, by the home computing system, executed layers of the data analytic model until the predetermined layer of the data analytic model has a minimum number of nodes, wherein the minimum number of nodes is based on the predetermined amount of generated traffic data between the home computing system and the public computing cloud.   
     
     
         11 . The method  claim 8 , the method further comprising:
 executing, by the home computing system, executed layers of the data analytic model until a first layer is reached having unrelated data to source data;   sending the unrelated data to the public computing cloud; and   executing, by the public computing cloud, the remaining layers utilizing the unrelated data.   
     
     
         12 . The method  claim 8 , the method further comprising:
 executing, by the home computing system, all layers of the data analytic model that have fixed parameters, wherein all said layers comprises a last layer; and   sending, by the home computing system, output data from the last layer having the fixed parameters to the public computing cloud; and   executing, by the public computing cloud, the remaining layers of the data analytic model.   
     
     
         13 . The method of  claim 3 , wherein the data analytic model comprises a deep neural network. 
     
     
         14 . The method of  claim 1  further comprising:
 when the error measure does not exceed the predetermined threshold, continue streaming, by the home computing system, the device data to the public computing cloud without sending corrective data. 
 
     
     
         15 . A home computing system supporting at least one Internet of Things (IoT) device, the home computing system comprising:
 a communications gateway configured to interface with the at least one IoT device;   a cloud interface configured to exchange information with a public computing cloud;   a processor for executing computer-executable instructions;   a memory storing the computer-executable instructions that when executed by the processor cause the home computing system to:
 obtain, via the communications gateway, device data from at least one IoT device configured at the home computing system; 
 streaming, via the cloud interface, the device data to a public computing cloud; 
 providing, by the public computing cloud, the device data to a data analytic model that the public computing cloud is executing for the home computing system; 
 in response to the streaming, receive a first predictive result from the public computing cloud; 
 apply the first predictive result to the at least one IoT device; 
 determine an error measure based on the first predictive result and corrections information to the first predictive result; and 
 when the error measure exceeds a predetermined threshold, send the corrections information to the public computing cloud. 
   
     
     
         16 . The home computing system of  claim 15 , wherein the memory storing the computer-executable instructions that when executed by the processor further cause the home computing system to:
 in response to the sending the corrections information, continue streaming the device data to the public computing cloud;   in response to the continued streaming, receive a second predictive result from the public computing cloud; and   apply the second predictive result to the at least one IoT device.   
     
     
         17 . A home computing system supporting at least one Internet of Things (IoT) device, the home computing system comprising:
 a communications gateway configured to interface with the at least one IoT device;   a cloud interface configured to exchange information with a public computing cloud;   a processor for executing computer-executable instructions;   a memory storing the computer-executable instructions that when executed by the processor cause the home computing system to:
 obtain, from communications gateway, a source data stream from one or more IoT devices; 
 execute a first sub-model of a data analytic model for the source data stream, wherein the data analytic model comprises a plurality of sub-models, wherein the plurality of sub-models comprises the first sub-model, and wherein each of the plurality of sub-models comprises a different subset of layers of the data analytic model; 
 obtain transformed data from the first sub-model of the data analytic model; 
 send, via the cloud interface, the transformed data to the public computing cloud, wherein the public computing cloud executes a second sub-model of the data analytic model; 
 in response to the sending, receive output data from the public computing cloud, wherein the output data is provided via the second sub-model of the data analytic model; 
 determine a predictive result from the output data; and 
 apply the predictive result to the at least one IoT device. 
   
     
     
         18 . The home computing system of  claim 17 , wherein the first sub-model comprises an input processing layer. 
     
     
         19 . The home computing system of  claim 18 , wherein the plurality of sub-models further comprises a third sub-model and wherein the memory storing the computer-executable instructions that when executed by the processor further cause the home computing system to:
 execute the third sub-model, wherein the second sub-model comprises an output layer.   
     
     
         20 . The home computing system of  claim 17 , wherein the memory storing the computer-executable instructions that when executed by the processor further cause the home computing system to:
 execute the first sub-model until a predetermined layer of the data analytic model is reached; and   send processed data from the predetermined layer to the public computing cloud.