The traditional non-intrusive load monitoring (NILM) algorithms are mostly based on classification models, which have several deficiencies. Firstly, a large amount of labeled data is required to train the classification model. Secondly, these algorithms cannot identify unknown devices that frequently encountered in practical application. Finally, these models have poor performance in versatility which means they only adapt to the trained data. These shortcomings greatly influence the practicality of these NILM algorithms. To tackle these problems, this paper has proposed a non-intrusive adaptive load identification model based on the Siamese network, which uses both the V-I trajectory and active power as the load signatures. The Siamese network is utilized to calculate the similarity of the V-I trajectory, and the load identification is realized by matching the signature with the feature library. Through adding new features to the feature library dynamically, the identification of unknown load can be realized. In addition, the Siamese network is a typical network for few-shot learning, thus the proposed model can be trained with a small number of samples to achieve ideal recognition effect. At last, the validity and versatility of the model are verified in PLAID dataset and COOLL dataset.
As renewable energy increasingly penetrates into electricity-heat integrated energy system (IES), the severe challenges arise for system reliability under uncertain generations. A two-stage approach consisting of pre-scheduling and re-dispatching coordination is introduced for IES under wind power uncertainty. In pre-scheduling coordination framework, with the forecasted wind power, the robust and economic generations and reserves are optimized. In re-dispatching, the coordination of electric generators and combined heat and power (CHP) unit, constrained by the pre-scheduled results, are implemented to absorb the uncertain wind power prediction error. The dynamics of building and heat network is modeled to characterize their inherent thermal storage capability, being utilized in enhancing the flexibility and improving the economics of IES operation; accordingly, the multi-timescale of heating and electric networks is considered in pre-scheduling and re-dispatching coordination. In simulations, it is shown that the approach could improve the economics and robustness of IES under wind power uncertainty by taking advantage of thermal storage properties of building and heat network, and the reserves of electricity and heat are discussed when generators have different inertia constants and ramping rates.
As is known to all that more and more sub-health problems have been induced by weight concerns. Due to the universality and the popularity of Android Smart Phone in the domestic and foreign markets, it is possible for us to develop a real-time weight management APP software based on Android Smart phones. Working out a kind of smart insole with a wireless communication module is also necessary for the success of data transmission and data processing through the sensor in the insoles. Such a system can identify the current state of bodies' weight and sitting posture according to the plantar pressure station and will remind the users to stand up and move around to avoid a long-term sitting. It has been pointed out that this kind of system has its own profound and practical significance for the application of Smart phones in the health management.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.