Research On Dynamic Load Forecasting And Energy Saving Control Strategy About Central Heating System

With the rapid development of national economy in our country,people is higher and higher requirement for the living environment of the comfort.The central heating is an important basic cause of our country,and it is an important means to ensure the comfort of people's living environment in the north of china.At present,China's energy situation is grim in the environmental protection,and the extensive central heating mode does not meet the requirements of green development.Relying on advanced technology and control strategy to ensure the high efficiency and energy saving of central heating system is the trend of the development of central heating system.With the development of metering and monitoring technology,network control technology and information processing technology,relying on these advanced technologies to study the energy saving control strategy of building central heating system to improve the energy efficiency of central heating system has become an important content of research and attention in related fields.Based on the data of the heating technology platform of a thermal power company in Shaanxi Province,considering the dynamic load regulation requirements,the load forecasting method with dynamic adjustment characteristics is studied for the purpose of the end load forecast.On this basis,the end of the central heating system equipment energy saving control strategy and heat transfer station system energy saving control strategy,with a view to improving the central heating system operation energy efficiency.Firstly,this paper analyzes the existing problems in the variable flow control strategy and the thermal load forecasting method of the existing heating system.The current flow control strategy of the current heating system mainly includes "temperature difference" and "differential pressure" control strategies.They are all based on the central effect of the system heat load control,and can't fully meet the heating system at the end of the dynamic adjustment requirements of users and ensure the end of the user's thermal comfort.With the development of heating system measurement and monitoring technology,we can easily obtain the environment and operation parameters of end users,using these parameters,research on suitable dynamic load forecasting method,improve the existing heating system of variable flow control is the core content of this paper.Through the simple analysis of the factors that affect the change of heat load,it is found that the load variation of heating system is influenced by many factors and has strong nonlinearity and uncertainty.Based on the simple analysis of the commonly used load forecasting algorithms,it is found that the current thermal load forecasting algorithm has many limitations,such as the complexity of the algorithm,focus on the concentration effect,and not possess the dynamic regulation characteristics.In order to solve the problems existing in the current thermal load forecasting algorithm.In this paper,the moving polynomial least squares algorithm is introduced based on the similarity of load data prediction and curve fitting.Considering that the load change of the heating system is more gentle and the trend is obvious,the improved weighted moving average algorithm is used to predict the terminal load..In this paper,we use the same thermal load data from the actual engineering,the mobile polynomial least square prediction model,the improve the weighted moving average algorithm prediction model and the BP neural network algorithm which is hotspot algorithm of the current load forecasting field are used to predict the calculation,and the predicted results are compared and analyzed.According to the prediction results show: moving polynomial least squares algorithm and the improved weighted moving average algorithm are smaller average error than BP neural network algorithm,and the algorithm is simpler than BP neural network algorithm,the required data is less than BP neural network algorithm,and they are more suitable than BP neural network algorithm for central heating at the end of the system engineering application of heat load forecasting.Finally,based on the results of the dynamic heat load forecasting of the terminal,rely on the function of the network control and management platform.In this paper,an energy-saving control strategy based on dynamic prediction of end-user thermal load is proposed,which can realize the optimal operation of energy-saving operation of user's end equipment regulation and heat transfer station load regulation.in order to achieve on-demand heating and helps to improve the efficiency of the whole system,to achieve emission reduction targets.