Software defined drone network control system
Methods and systems are provided for controlling an unmanned aerial vehicle (UAV) swarm network including receiving, at a control terminal, an operator input defining a plurality of network performance directives, constructing a network control model representing the plurality of network performance directives, decomposing the network control model into a plurality of sub-models, generating, via the control terminal, a distributed UAV control model corresponding to each of the distributed sub-models, transmitting the generated distributed UAV control models to each of a plurality of UAVs of the UAV swarm network, executing, at each of the plurality of UAVs, at least one of the distributed UAV control models, and changing, responsive to the execution of the distributed UAV control models, an operating condition of at least one of the plurality of UAVs to satisfy the network performance directives.
1. A method for controlling an unmanned aerial vehicle (UAV) swarm network comprising:
receiving, at a control terminal, an operator input defining a plurality of network performance directives;
constructing a network control model representing the plurality of network performance directives;
decomposing the network control model into a plurality of sub-models, wherein the decomposition includes one or more of horizontal decomposition of horizontal couplings characterized by cross-node dependencies among variables controlled by different UAVs, vertical decomposition of vertical couplings characterized by cross-layer dependencies among variables controlled by the same UAV but belonging to different layers, or combinations thereof;
generating, via the control terminal, a respective distributed UAV control model corresponding to each of the distributed sub-models;
transmitting the generated distributed UAV control models to each of a plurality of UAVs of the UAV swarm network;
executing, at each of the plurality of UAVs, at least one of the distributed UAV control models; and
changing, responsive to the execution of the distributed UAV control models, an operating condition of at least one of the plurality of UAVs to satisfy the network performance directives by controlling one or more of a flight computer, a motor, a sensor, a camera, a propeller, a fan, an actuator, a servo, a control surface, an antenna, a sensor, a camera, a transceiver, a software-defined radio, a network router, or combinations thereof to change one or more of an altitude of the UAV, a trajectory of the UAV, a velocity of the UAV, an attitude of the UAV, a flight pattern of the UAV, a broadcast power, a transmission pattern, a transmission direction, a receive direction, a receive pattern, a network protocol, or combinations thereof.
2. The method of claim 1 , wherein the plurality of network performance directives includes prioritization, quantification, or both of one or more of energy consumption, QoS requirements, network protocols, network throughput, network data rate, geographic network coverage, or combinations thereof.
3. The method of claim 1 , wherein the plurality of network performance directives includes prioritization, quantification, or both of one or more of geographic UAV location, altitude, flight speed, dwell time, proximity requirements, return-to-base conditions, or combinations thereof.
4. The method of claim 1 , wherein the step of executing further comprises retrieving real-time network state information.
5. The method of claim 4 , wherein the real-time network state information includes one or more of locations of the plurality of UAVs, a network signal to noise ratio (SNR), routing tables, a queue status, battery levels of the plurality of UAVs, a ground distance, a TCP congestion window, a routing path, a transmission power, a modulation scheme, or combinations thereof.
6. The method of claim 1 , wherein the step of decomposition is performed by one or more of partial linearization, Taylor series linearization, Lagrangian duality, or combinations thereof.
7. The method of claim 4 , further comprising:
retrieving updated real-time network state information;
executing, at each of the plurality of UAVs responsive to retrieval of the updated real-time network state information, at least one of the distributed UAV control models, at least one updated distributed UAV control model, or a combination thereof; and
changing, responsive to the execution of the distributed UAV control models or updated distributed UAV control models, a current operating condition of at least one of the plurality of UAVs.
8. A system for controlling an unmanned aerial vehicle (UAV) swarm network comprising:
a control terminal, having a memory and a processor, the memory including instructions that, when executed by the processor cause the control terminal to:
receive an input defining a plurality of network performance directives;
construct a network control model representing the plurality of network performance directives,
decompose the network control model into a plurality of sub-models, wherein the decomposition includes one or more of horizontal decomposition of horizontal couplings characterized by cross-node dependencies among variables controlled by different UAVs, vertical decomposition of vertical couplings characterized by cross-layer dependencies among variables controlled by the same UAV but belonging to different layers, or combinations thereof;
generate a respective distributed UAV control model corresponding to each of the distributed sub-models, and
transmit the generated distributed UAV control models to each of a plurality of UAVs of the UAV network; and
the plurality of UAVs, each configured to:
execute at least one of the distributed UAV control models; and
change, responsive to the execution of the distributed UAV control models, an operating condition of at least one of the plurality of UAVs to satisfy the network performance directives by controlling one or more of a flight computer, a motor, a sensor, a camera, a propeller, a fan, an actuator, a servo, a control surface, an antenna, a sensor, a camera, a transceiver, a software-defined radio, a network router, or combinations thereof to change one or more of an altitude of the UAV, a trajectory of the UAV, a velocity of the UAV, an attitude of the UAV, a flight pattern of the UAV, a broadcast power, a transmission pattern, a transmission direction, a receive direction, a receive pattern, a network protocol, or combinations thereof.
9. The system of claim 8 , wherein the plurality of network performance directives includes prioritization, quantification, or both of one or more of energy consumption, QoS requirements, network protocols, network throughput, network data rate, geographic network coverage, or combinations thereof.
10. The system of claim 8 , wherein the plurality of network performance directives includes prioritization, quantification, or both of one or more of geographic UAV location, altitude, flight speed, dwell time, proximity requirements, return-to-base conditions, or combinations thereof.
11. The system of claim 10 , wherein the return-to-base conditions include a minimum threshold detected battery life, a prescribed return time, a failure detection, detection of an atmospheric condition, impact detection, or combinations thereof.
12. The system of claim 8 , wherein executing at least one of the distributed UAV control models further comprises retrieving real-time network state information.
13. The system of claim 8 , wherein decomposing the network control model further comprises one or more of partial linearization, Taylor series linearization, Lagrangian duality, or combinations thereof.
14. The system of claim 12 , wherein each of the plurality of UAVs is further configured to:
retrieve updated real-time network state information;
re-execute, responsive to retrieval of the updated real-time network state information, at least one of the distributed UAV control models, at least one updated distributed UAV control model, or a combination thereof; and
change, responsive to the execution of the distributed UAV control models or updated distributed UAV control models, a current operating condition of at least one of the plurality of UAVs.