Loading...
3 results
Search Results
Now showing 1 - 3 of 3
- Towards using Low-Cost Opportunistic Energy Sensing for Promoting Energy ConservationPublication . Nunes, Nuno J.; Pereira, Lucas; Nisi, ValentinaThis position paper discusses how to leverage low-cost energy sensing to opportunistically develop activity-based approaches to energy conservation. Based on our extensive experience developing low-cost sensing infrastructures and long term deployment of ecofeedback systems, we discuss the possibility of unobtrusively inferring domestic activities from the overall aggregated energy consumption of households. We then postulate how the combination of this information with daily household activities could lead to more effective and meaningful ways to re-aggregate residential energy consumption for the purpose of ecofeedback. Here we briefly present a practical approach towards this new research direction that leverages HCI related methods, in particular using the day reconstruction method to provide semi-supervised approaches for automatic detection of household activities.
- What-a-Watt: exploring electricity production literacy through a long term eco-feedback studyPublication . Quintal, Filipe; Pereira, Lucas; Nunes, Nuno J.; Nisi, ValentinaThis paper presents the design, implementation and evaluation of an eco-feedback system capable of providing detailed household consumption information and also real-time production breakdown per energy source. We build on recent studies reporting an increased awareness generated by eco feedback systems that also integrate micro-production information, taking advantage of a closed grid production network on an island with a high concentration of renewables, we deployed the What-a-Watt system in a building with 9 households for a period of 34 consecutive weeks. Results show that all the participating families have shown increased awareness of the production and distribution of electricity, thus becoming more familiarized with concepts such as the different sources of energy and how their availability relates to external variables such as weather conditions and time of day. Furthermore, our results also show, that the families using our system have managed to reduce their overall consumption. This research is a first attempt to provide more effective eco-feedback systems to consumers by integrating complex Smartgrid information in the feedback.
- Implementation Strategy of Convolution Neural Networks on Field Programmable Gate Arrays for Appliance Classification Using the Voltage and Current (V-I) TrajectoryPublication . Baptista, Darío; Mostafa, Sheikh Shanawaz; Pereira, Lucas; Sousa, Leonel; Dias, Fernando MorgadoSpecific information about types of appliances and their use in a specific time window could help determining in details the electrical energy consumption information. However, conventional main power meters fail to provide any specific information. One of the best ways to solve these problems is through non-intrusive load monitoring, which is cheaper and easier to implement than other methods. However, developing a classifier for deducing what kind of appliances are used at home is a difficult assignment, because the system should identify the appliance as fast as possible with a higher degree of certainty. To achieve all these requirements, a convolution neural network implemented on hardware was used to identify the appliance through the voltage and current (V-I) trajectory. For the implementation on hardware, a field programmable gate array (FPGA) was used to exploit processing parallelism in order to achieve optimal performance. To validate the design, a publicly available Plug Load Appliance Identification Dataset (PLAID), constituted by 11 different appliances, has been used. The overall average F-score achieved using this classifier is 78.16% for the PLAID 1 dataset. The convolution neural network implemented on hardware has a processing time of approximately 5.7 ms and a power consumption of 1.868 W.