Optimal sensor placement for monitoring and controlling greenhouse internal environments

In large greenhouses with information and communication technology capability, environmental conditions can be measured and communicated to control the internal environment. However, in such greenhouses, it is difficult to control the internal environment uniformly and appropriately. Additionally, there is uncertainty regarding whether the data measured at a particular location accurately represents the entire greenhouse environment. Furthermore, the locations of sensors are usually determined based on the experience of growers and the greenhouse designers. To accurately measure the internal environment of a greenhouse, it is necessary to properly select the installation locations of the sensors. The objective of this study was to determine the optimal sensor placement for monitoring and controlling the internal environment of a greenhouse. The study greenhouse was an eight-span plastic greenhouse growing Irwin mango crops. Air temperature data measured at nine locations in the greenhouse were used. All of the possible combinations of monitoring locations were evaluated, and optimal sensor placements were selected according to the number of sensors. The optimisation was conducted using two methods: error-based sensor placement and entropy-based sensor placement. Using the former approach, sensor locations for which the monitored data were close to the reference value, i.e. the average data of all the measurement locations, were selected. Using the latter approach, sensor locations influenced by the external weather conditions resulting in poor environmental control were selected. Using these methods, optimal sensor locations for representing the entire environment of the facility and for detecting areas with significant air temperature variations were determined.