KEYWORDS: Solar energy, Data modeling, System integration, Reliability, Mathematical optimization, Power consumption, Atmospheric modeling, Education and training, Power grids, Wind energy
The multiple loads of the integrated energy system have the characteristics of complex coupling, strong volatility, and strong randomness, and accurate prediction is the foundation and guarantee for optimizing the scheduling of the integrated energy system. An integrated energy system scheduling method based on SSA-BI-GRU multivariate load forecasting is proposed. Firstly, in order to explore the relationships between data more fully, the SSA-BI-GRU algorithm is proposed. Random forest regression model and cross-telecommunication validation are introduced into the data processing module. Then, we construct an integrated energy system optimization scheduling model to incorporate system reliability into the objective function. Finally, the load prediction results of the SSA-BI-GRU model are used as input to solve the IES scheduling problem using the improved MOGWO algorithm. The results show that SSA-BI-GRU improves the accuracy and speed of load forecasting, and the established multi-energy flow coupling optimization scheduling model achieves the economic, efficient, and reliable operation of IES.
Based on the shortcomings of MVVM framework in enterprise level applications, this paper proposes a flexible common framework for enterprise level Web applications based on MVVM framework, designs core functions such as custom tag components and dynamic page component assembly mechanism and implements them based on the lightweight front-end framework knockout. The public framework designed and implemented in this paper introduces MVVM excellent architecture mode, flexible customization mode and high browser compatibility for traditional enterprises.
KEYWORDS: Data modeling, Fusion energy, Data fusion, Visualization, Data communications, Visual process modeling, Telecommunications, Software development, Computer architecture
With the rapid development of new power systems and smart energy, data sources for energy equipment are being greatly expanded, and integrated power scenarios are becoming more sophisticated and complex. As a visualization tool that can quickly build smart energy scenarios, configuration software has been unable to efficiently respond to the increasing number of cross-system and multi-granularity display requirements. In order to address the serious shortcomings of configuration software in data display, this paper proposes a new multi-source data fusion scheme that achieves the linkage effect between equipment model attributes and multi-source binding data via flexible and configurable multi-source data selection components and dynamically assigned functions. At the same time, the hybrid communication mechanism is used to optimize the data refresh performance, and finally, multi-source data fusion of a single model is realized, which improves energy visualization accuracy. In the end, an example scenario is compared to the existing solution to validate the paper's proposed scheme's simplicity, flexibility, and agility.
Dialogue system uses natural language as a medium to achieve friendly communication between humans and machines. The performance of intent detection is crucial to the effectiveness of a task-oriented dialogue system. When developing a task-oriented dialogue system in a specific domain, users typically express multiple intents in the same sentence. In this study, we compare two approaches for multi-intent detection at the sentence level, which aims to investigate multi-intent detection for task-oriented dialogue systems based on joint learning. Experiment results on the ATIS and MixATIS datasets show that the multi-classification approach improves slot prediction by combining relevant intent information, whereas the multi-label approach based on joint learning improves intent detection by making predictions at each possible intent.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.