دانلود رایگان مقاله طراحی مجموعه سنسور برای ذخیره انرژی در ساختمان

Abstract

There is a growing desire to measure the operational performance of buildings e often many buildings simultaneously e but the cost of sensors and complexity of deployment is a significant constraint. In this paper, we present an approach to minimising the cost of sensing by recognising that researchers are often not interested in the raw data itself but rather some inferred performance metric (e.g. high CO2 levels may indicate poor ventilation). We cast the problem as one of constrained optimisation e specifically, as a bounded knapsack problem (BKP) e to choose the best sensors for the set given each sensor's predictive value and cost. Training data is obtained from a field study comprising a wide range of possible sensors from which a minimum set can be extracted. We validate the method using reliable selfreported event diaries as a measure of actual performance. Results show that the method produces sensors sets that are good predictors of performance and the optimal sets vary substantially with the constraint parameters. Furthermore, valuable yet expensive sensors are often not chosen in the optimal set due to strong co-incidence of sensor signals. For example, light level and sound level often increase at the same time. The overall implication of the work is that a large number of co-incident low-cost sensors can be used to build up a picture of building performance, without significantly compromising information content, and this could have major benefits for the smart metering industry.

6. Conclusion and future

work In this paper, we have presented a process for designing sensor sets to capture energy events in buildings. The key contributions lie in the use of random forests to produce a measure of sensor value a priori, and the implementation of a bounded knapsack problem (BKP) solver that chooses an optimum sensor set given a set of costs and values. Through a field study in 4 UK homes, we have illustrated how random forests can be used to output a measure of predictive value using the Gini impurity measure, and how this measure e when combined with an appropriate cost measure, e.g. financial cost e can be used to generate sensor sets given designer constraints. Through this, we have also shown that more valuable but expensive sensors such as CO2 are often not included in the sets due to their high cost. Furthermore, we have shown that CO2 and light sensors are particularly predictable, with a mean predictable proportion for both of 0.4 bits from the other sensors used in our study of domestic buildings (temperature, humidity and sound level).