Automated network control systems that adapt network configurations based on the local network environment

1. A network control system comprising:

a sensor interface to obtain data from a plurality of sensors;

a first subsystem comprising a plurality of distributed short-term memory modules, each short-term memory module associated with a wireless communication device, the first subsystem to adjust a communications parameter for one or more of the wireless communication devices based on data from one or more of the plurality of sensors; and

a second subsystem coupled to the sensor interface and to the first subsystem comprising a processor, the processor including one or more substrates and logic coupled to the one or more substrates, wherein the logic is implemented at least partly in one or more of configurable logic or fixed-functionality hardware logic, the logic coupled to the one or more substrates to:

determine, via a neural network, a prediction of future performance of a wireless network based on a state of a network environment, wherein the state of the network environment includes information from the first subsystem and location information about the wireless communication devices and other objects in the network environment, wherein the information from the first subsystem is to include one or more received signal strength indication (RSSI) maps, each RSSI map associated with a channel state between an access point and one of the wireless communication devices;

determine a change in network configuration to improve a quality of communications in the wireless network based on the prediction of future performance of the wireless network;

receive a plurality of time-stamped RSSI maps, wherein each of the plurality of time-stamped RSSI maps is associated with an object location, a time of day, a day of year, and one or more of temperature or humidity levels within the network environment;

generate a plurality of generic path loss models based on the plurality of time-stamped RSSI maps; and

record a sequence of events that cause a significant drop in RSSI;

wherein to determine a change in network configuration is based on the plurality of generic path loss models and the sequence of events.

2. The network control system of claim 1 , wherein to determine a change in network configuration to improve a quality of communications in the wireless network the logic coupled to the one or more substrates is to adjust one or more network parameters, and wherein the one or more network parameters includes one or more of an increase in transmission power by one of the wireless communication devices or a change in an access point to be connected to the one of the wireless communication devices.

3. The network control system of claim 1 , wherein the first subsystem comprises a short-term subsystem and the second subsystem comprises a long-term subsystem, and

wherein the prediction of future performance of the wireless network comprises a prediction of future RSSI values based on determined relationships between the RSSI maps and object locations relative to the access point and the wireless communication devices.

4. The network control system of claim 3 , wherein the system is to track a plurality of the wireless communication devices and a plurality of the other objects, and

wherein the prediction of future performance of the wireless network includes a prediction of future attenuation in RSSI values associated with a tracked moving object relative to the access point and a tracked one of the wireless communication devices.

5. The network control system of claim 3 , wherein the logic coupled to the one or more substrates is further to:

receive additional channel state information; and

determine one or more of a positioning of one or more of the objects in the network environment or a prediction of future quality of service (QoS) for the wireless network.

6. A semiconductor apparatus comprising:

one or more substrates; and

logic coupled to the one or more substrates, wherein the logic is implemented at least partly in one or more of configurable logic or fixed-functionality hardware logic, the logic coupled to the one or more substrates to:

adjust, via a first subsystem, a communications parameter for one or more wireless communication devices based on data from one or more of a plurality of sensors;

determine, via a neural network, a prediction of future performance of a wireless network based on a state of a network environment, wherein the state of the network environment includes information from the first subsystem and location information about the one or more wireless communication devices and other objects in the network environment, wherein the information from the first subsystem is to include one or more received signal strength indication (RSSI) maps, each RSSI map associated with a channel state between an access point and one of the wireless communication devices;

determine a change in network configuration to improve a quality of communications in the wireless network based on the prediction of future performance of the wireless network;

receive a plurality of time-stamped RSSI maps, wherein each of the plurality of time-stamped RSSI maps is associated with an object location, a time of day, a day of year, and one or more of temperature or humidity levels within the network environment;

generate a plurality of generic path loss models based on the plurality of time-stamped RSSI maps; and

record a sequence of events that cause a significant drop in RSSI;

wherein to determine a change in network configuration is based on the plurality of generic path loss models and the sequence of events.

7. The semiconductor apparatus of claim 6 , wherein to determine a change in network configuration to improve a quality of communications in the wireless network the logic coupled to the one or more substrates is to adjust one or more network parameters, and wherein the one or more network parameters includes one or more of an increase in transmission power by one of the wireless communication devices or a change in an access point to be connected to the one of the wireless communication devices.

8. The semiconductor apparatus of claim 6 , wherein the first subsystem comprises a short-term subsystem, and

wherein the prediction of future performance of the wireless network comprises a prediction of future RSSI values based on determined relationships between the RSSI maps and object locations relative to the access point and the wireless communication devices.

9. The semiconductor apparatus of claim 8 , wherein the logic coupled to the one or more substrates is to track a plurality of the wireless communication devices and a plurality of the other objects, and

wherein the prediction of future performance of the wireless network includes a prediction of future attenuation in RSSI values associated with a tracked moving object relative to the access point and a tracked one of the wireless communication devices.

10. The semiconductor apparatus of claim 8 , wherein the logic coupled to the one or more substrates is further to:

receive additional channel state information; and

determine one or more of a positioning of one or more of the objects in the network environment or a prediction of future quality of service (QoS) for the wireless network.

11. The semiconductor apparatus of claim 6 , wherein the logic coupled to the one or more substrates includes transistor channel regions that are positioned within the one or more substrates.

12. At least one non-transitory computer readable storage medium comprising a set of instructions which, when executed by a computing system, cause the computing system to:

adjust, via a first subsystem, a communications parameter for one or more wireless communication devices based on data from one or more of a plurality of sensors;

determine, via a neural network, a prediction of future performance of a wireless network based on a state of a network environment, wherein the state of the network environment includes information from the first subsystem and location information about the one or more wireless communication devices and other objects in the network environment, wherein the information from the first subsystem is to include one or more received signal strength indication (RSSI) maps, each RSSI map associated with a channel state between an access point and one of the wireless communication devices;

determine a change in network configuration to improve a quality of communications in the wireless network based on the prediction of future performance of the wireless network;

receive a plurality of time-stamped RSSI maps, wherein each of the plurality of time-stamped RSSI maps is associated with an object location, a time of day, a day of year, and one or more of temperature or humidity levels within the network environment;

generate a plurality of generic path loss models based on the plurality of time-stamped RSSI maps; and

record a sequence of events that cause a significant drop in RSSI;

wherein to determine a change in network configuration is based on the plurality of generic path loss models and the sequence of events.

13. The at least one non-transitory computer readable storage medium of claim 12 , wherein to determine a change in network configuration to improve a quality of communications in the wireless network, the instructions, when executed, cause the computing system to adjust one or more network parameters, and wherein the one or more network parameters includes one or more of an increase in transmission power by one of the wireless communication devices or a change in an access point to be connected to the one of the wireless communication devices.

14. The at least one non-transitory computer readable storage medium of claim 12 , wherein the first subsystem comprises a short-term subsystem, and

wherein the prediction of future performance of the wireless network comprises a prediction of future RSSI values based on determined relationships between the RSSI maps and object locations relative to the access point and the wireless communication devices.

15. The at least one non-transitory computer readable storage medium of claim 14 , wherein the instructions, when executed, further cause the computing system to track a plurality of the wireless communication devices and a plurality of the other objects, and

wherein the prediction of future performance of the wireless network includes a prediction of future attenuation in RSSI values associated with a tracked moving object relative to the access point and a tracked one of the wireless communication devices.

16. The at least one non-transitory computer readable storage medium of claim 14 , wherein the instructions, when executed, further cause the computing system to:

receive additional channel state information; and

determine one or more of a positioning of one or more of the objects in the network environment or a prediction of future quality of service (QoS) for the wireless network.

17. A method of automated network control, comprising:

adjusting, via a first subsystem, a communications parameter for one or more wireless communication devices based on data from one or more of a plurality of sensors;

determining, via a neural network, a prediction of future performance of a wireless network based on a state of a network environment, wherein the state of the network environment includes information from the first subsystem and location information about the one or more wireless communication devices and other objects in the network environment wherein the information from the first subsystem includes one or more received signal strength indication (RSSI) maps, each RSSI map associated with a channel state between an access point and one of the wireless communication devices;

determining a change in network configuration to improve a quality of communications in the wireless network based on the prediction of future performance of the wireless network;

receiving a plurality of time-stamped RSSI maps, wherein each of the plurality of time-stamped RSSI maps is associated with an object location, a time of day, a day of year, and one or more of temperature or humidity levels within the network environment;

generating a plurality of generic path loss models based on the plurality of time-stamped RSSI maps; and

recording a sequence of events that cause a significant drop in RSSI;

wherein determining a change in network configuration is based on the plurality of generic path loss models and the sequence of events.

18. The method of claim 17 , wherein determining a change in network configuration to improve a quality of communications in the wireless network comprises adjusting one or more network parameters, and wherein the one or more network parameters includes one or more of an increase in transmission power by one of the wireless communication devices or a change in an access point to be connected to the one of the wireless communication devices.

19. The method of claim 17 , wherein the first subsystem comprises a short-term subsystem, and

wherein the prediction of future performance of the wireless network comprises a prediction of future RSSI values based on determined relationships between the RSSI maps and object locations relative to the access point and the wireless communication devices.

20. The method of claim 19 , further comprising tracking a plurality of the wireless communication devices and a plurality of the other objects,

wherein the prediction of future performance of the wireless network includes a prediction of future attenuation in RSSI values associated with a tracked moving object relative to the access point and a tracked one of the wireless communication devices.

21. The method of claim 19 , further comprising:

receiving additional channel state information; and

determining one or more of a positioning of one or more of the objects in the network environment or a prediction of future quality of service (QoS) for the wireless network.

22. The network control system of claim 1 , wherein the neural network is trained based on detecting and tracking positions of objects in a training environment and on expected RSSI values of network devices in the training environment, wherein at least one of the objects is a moving object that becomes an occluding object.

23. The semiconductor apparatus of claim 6 , wherein the neural network is trained based on detecting and tracking positions of objects in a training environment and on expected RSSI values of network devices in the training environment, wherein at least one of the objects is a moving object that becomes an occluding object.

24. The at least one non-transitory computer readable storage medium of claim 12 , wherein the neural network is trained based on detecting and tracking positions of objects in a training environment and on expected RSSI values of network devices in the training environment, wherein at least one of the objects is a moving object that becomes an occluding object.

25. The method of claim 17 , wherein the neural network is trained based on detecting and tracking positions of objects in a training environment and on expected RSSI values of network devices in the training environment, wherein at least one of the objects is a moving object that becomes an occluding object.