Abstract
For the design and planning of gas-fired boiler system, the load of gas-fired boiler is an important basic data. Load clustering analysis, combined with the application of data mining technology and gas boiler system, excavates the hidden load patterns in a large number of disordered and irregular loads, and classifies them, so as to solve many problems in gas boiler system. The current load clustering methods have more or less problems. The invention first carries out data PVA dimension reduction processing on the huge gas data, and then carries out cluster analysis. In the actual application of gas-fired boilers, the data objects we are faced with are usually unbalanced data sets. In order to solve the problem of sample imbalance, we use the FCM-SMOTE algorithm to oversample the clustered data to make the data set into a balanced data set.
Highlights
The research on load clustering of gas-fired boiler system is to classify gas load scientifically and effectively, and user load clustering is to dig out the relationship and composition of different types and areas of load through cluster analysis[1]
The results show that the fuzzy Cmeans (FCM) clustering results obtained from the data processed by sum standardization and maximum standardization are the most accurate, but the clustering effect is not good for high-dimensional data sets with a large number of features, and the computation is large and inefficient
The classification results of the unbalanced data sets are more likely to be biased towards the positive sample, which ignores the important information contained in the negative sample, making the decision boundary of the classifier different from the actual spur results of the positive and negative samples
Summary
The research on load clustering of gas-fired boiler system is to classify gas load scientifically and effectively, and user load clustering is to dig out the relationship and composition of different types and areas of load through cluster analysis[1]. The load cluster analysis combines the data mining technology and the application of the gas boiler system, through the data mining to analyze the gas load characteristics, and excavates the hidden load patterns in a large number of disordered and irregular loads, and classify it, through the typical load curve, solve many problems in the gas boiler system, such as gas load forecasting, demand side response analysis. Based on the classification of load data, the gas consumption patterns of different gas users can support gas companies to carry out orderly heating, offpeak management, time-sharing gas and other market competition strategies and provide more personalized heating services. It helps to improve the understanding of the gas consumption patterns of different gas users, so as to carry out more efficient demand side management. Users can adjust consumption strategies more economically and optimally according to the problems found in load classification, which reduces costs, and improves energy efficiency. In view of the importance of load clustering in gas systems and the difficulties faced by existing traditional methods, it is necessary to study new effective load classification methods to meet the current load clustering needs
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
