Agricultural sensor placement and fault detection in wireless sensor networks

Abstract

Disclosed are various embodiments for optimized sensor deployment and fault detection in the context of agricultural irrigation and similar applications. For instance, a computing device may execute a genetic algorithm (GA) routine to determine an optimal sensor deployment scheme such that a mean-time-to-failure (MTTF) for the system is maximized, thereby improving communication of sensor measurements. Moreover, in various embodiments, a centralized fault detection scheme may be employed and a soil moisture of a field can be determined by statistically inferring soil moistures at locations of faulty nodes using spatial and temporal correlations.

1 . A system for fault detection in an agricultural sensor network, comprising:
 a plurality of sensors distributed in a plurality of regions of a field;   at least one computing device; and   program instructions stored in memory and executable by the at least one computing device that, when executed, direct the at least one computing device to:
 monitor each of the sensors in the agricultural sensor network by collecting data from each of the sensors wirelessly; 
 detect a fault in at least one of the sensors, wherein the fault is identified based at least in part on (a) historical sensor data collected by the at least one of the sensors, and (b) data corresponding to a neighboring one of the at least one of the sensors; and 
 in response to the fault being detected for the at least one of the sensors, generate a metric for the field or for each of the regions of the field, wherein the metric is generated using a measurement inferred for a location of the at least one of the sensors in which the fault is detected. 
   
     
     
         2 . The system of  claim 1 , wherein the at least one computing device is implemented in a single controller centrally located with respect to each of the sensors. 
     
     
         3 . The system of  claim 2 , wherein the single controller is attached to an irrigation system. 
     
     
         4 . The system of  claim 2 , wherein:
 the at least one of the sensors is a soil moisture sensor;   the metric is a soil moisture metric; and   the measurement is a soil moisture measurement inferred for the location of the at least one of the sensors in which the fault is detected.   
     
     
         5 . The system of  claim 4 , further comprising program instructions stored in memory and executable by the at least one computing device that, when executed, direct the irrigation system to perform an irrigation task based at least in part on the soil moisture metric. 
     
     
         6 . The system of  claim 4 , wherein the fault detected in the soil moisture sensor is at least one of: a communication error, battery exhaustion, or electronic device failure. 
     
     
         7 . The system of  claim 4 , wherein the at least one computing device is further directed to determine a validity of the measurement obtained from the at least one of the sensors, wherein the validity of the measurement is determined by comparing actual measurement data obtained from the at least one of the sensors to data inferred from a spatial correlation and a temporal correlation. 
     
     
         8 . The system of  claim 7 , wherein the fault in the at least one of the sensors is detected based at least in part on a consistency check with a weighted average of (i) measurements obtained from the neighboring one of the at least one of the sensors, and (ii) measurements obtained from the historical sensor data collected by the at least one of the sensors. 
     
     
         9 . A method for fault detection in an agricultural sensor network, the method comprising:
 monitoring, via at least one computing device, each of a plurality of sensors in the agricultural sensor network by collecting data from each of the sensors wirelessly, the plurality of sensors being distributed in a plurality of regions of a field;   detecting, via the at least one computing device, a fault in at least one of the sensors, wherein the fault is identified based at least in part on (a) historical sensor data collected by the at least one of the sensors, and (b) data corresponding to a neighboring one of the at least one of the sensors; and   in response to the fault being detected for the at least one of the sensors, generating, via the at least one computing device, a metric for the field or for each of the regions of the field, wherein the metric is generated using a measurement inferred for a location of the at least one of the sensors in which the fault is detected.   
     
     
         10 . The method of  claim 1 , wherein the at least one computing device is implemented in a single controller centrally located with respect to each of the sensors. 
     
     
         11 . The method of  claim 10 , wherein the single controller is attached to a irrigation system. 
     
     
         12 . The method of  claim 10 , wherein:
 the at least one of the sensors is a soil moisture sensor;   the metric is a soil moisture metric; and   the measurement is a soil moisture measurement inferred for the location of the at least one of the sensors in which the fault is detected.   
     
     
         13 . The method of  claim 12 , further comprising directing the irrigation system to perform an irrigation task based at least in part on the soil moisture metric. 
     
     
         14 . The method of  claim 12 , wherein the fault detected in the soil moisture sensor is at least one of: a communication error, battery exhaustion, or electronic device failure. 
     
     
         15 . The method of  claim 12 , further comprising determining a validity of the measurement obtained from the at least one of the sensors, wherein the validity of the measurement is determined by comparing actual measurement data obtained from the at least one of the sensors to data inferred from a spatial correlation and a temporal correlation. 
     
     
         16 . The system of  claim 15 , wherein the fault in the at least one of the sensors is detected based at least in part on a consistency check with a weighted average of (i) measurements obtained from the neighboring one of the at least one of the sensors, and (ii) measurements obtained from the historical sensor data collected by the at least one of the sensors. 
     
     
         17 . A non-transitory computer readable medium comprising a program executable by at least one computing device, wherein, when executed, the program causes the at least one computing device to at least:
 monitor each of a plurality of sensors in the agricultural sensor network by collecting data from each of the sensors wirelessly, the plurality of sensors being distributed in a plurality of regions of a field;   detect a fault in at least one of the sensors, wherein the fault is identified based at least in part on (a) historical sensor data collected by the at least one of the sensors, and (b) data corresponding to a neighboring one of the at least one of the sensors; and   in response to the fault being detected for the at least one of the sensors, generate a metric for the field or for each of the regions of the field, wherein the metric is generated using a measurement inferred for a location of the at least one of the sensors in which the fault is detected.   
     
     
         18 . The non-transitory computer readable medium of  claim 17 , wherein the at least one computing device is implemented in a single controller centrally located with respect to each of the sensors. 
     
     
         19 . The non-transitory computer readable medium of  claim 17 , the at least one of the sensors is a soil moisture sensor;
 the metric is a soil moisture metric; and   the measurement is a soil moisture measurement inferred for the location of the at least one of the sensors in which the fault is detected.   
     
     
         20 . The non-transitory computer readable medium of  claim 20 , wherein the fault detected in the soil moisture sensor is at least one of: a communication error, battery exhaustion, or electronic device failure.