Study On The Rule Of Gas-consumption In The Resident's Life And The Short-term Demand Forecast

With the development of small towns'economy, especially the improvement of requirement of people's life and survival environment, natural gas, as an ideal,clean,high quality energy source, has become one of the most important fuels for small town, gas industry can develop healthily and rapidly. So it is a very important research task to understand the gas-consumptive orderliness and forecast city gas load, for one hand, it will affect the planning of city gas pipe network, on the other hand, it is connected to the investment benefits and security of entire natural gas pipelines, and it's meaningful for urban gas optimizing attemperation and gas pipeline optimizing operation.The dissertation analyses the observational data of the small town in Sichuan Province in 2005, bring forward the recommendation of the gas-consumption guide line,mensal peaking factor,daily peaking factor and hourly peaking factor, then compare the difference and similarity of the consumptive orderliness between small town and big,middling city. This dissertation also introduce various methods to gas load forecasting, including: regression analytical method, time serial method, elasticity coefficient forecasting, artificial neural network forecasting model, experts system forecasting model, etc.. This dissertation emphasizes on artificial neural network forecasting model, introduces the rationale and algorithm and approaches about ANN. And then validate the correctness of theories by calculating instance with optimizing L-M algorithm. The outcomes are satisfied, by adopting different model, which include normal daily load forecasting and hour load forecasting. At last, compare the superiority and disadvantage of the result, bring forward the best method to load forecasting.