As a time-shifting load that is gradually popularized in the northern region, electric heating load has great adjustment potential. Because the electric heating operation characteristics are affected by many non-linear factors, the traditional equivalent thermal parameters model cannot accurately evaluate the regulation capability of individual electric heating load. Aiming at this problem, this paper proposes an evaluation method for the regulation capability of individual electric heating load based on radial basis function neural network. Firstly, electric heating load control experiments were carried out in a typical room of a residential quarter in winter and relevant experimental data were collected. Then, based on the operation data, the radial basis function neural network is used to evaluate the regulation capability of the individual electric heating load. Finally, the evaluation results based on radial basis function neural network are compared with those based on back propagation neural network and equivalent thermal parameters model. The results show that the proposed method has the least evaluation error and can more accurately evaluate the regulation capability of individual electric heating load.
The power supply side regulating capability of the power grid is limited, and it is important to dig deep into the load side regulation capability. Electro-heating load is a time-shifting load with the characteristics of small thermal inertia, fast response, high controllability, etc. It has the potential to participate in active power dispatching and control the power grid. When the electro-heating load is working, the indoor temperature curve is affected by many factors. It has a similar influence characteristic quantity, and a similar temperature rise and fall process is exhibited in the temparature setted range. When using the traditional equivalent thermal parameter to evaluate, the outdoor temperature at the end of the warming up or cooling down process is unknown, so the regulating potential of individual electro-heating load cannot be accurately evaluated. Therefore, this paper proposes a similarity-based support vector machine single electro-heating regulating potential evaluation method, and compared with the traditional equivalent thermodynamic model, it shows that this method has higher evaluation accuracy.
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.