Zadachyn, ViktorFrolov, OlegЗадачин, Віктор МихайловичФролов, Олег Васильович2023-05-032023-05-032023Zadachyn, V. M. Urban daily water demand forecasting / V. M. Zadachyn, O. V. Frolov // Вiсник Харкiвського нацiонального автомобiльно-дорожнього унiверситету : зб. наук. пр. / М-во освiти i науки України, Харків. нац. автомоб.-дор. ун-т ; редкол.: А. Г. Батракова (гол. ред.) та iн. – Харкiв, 2023. – Вип. 100. – С. 30–36.2219-5548https://dspace.khadi.kharkov.ua/handle/123456789/11613The problem of building models and methods of forecasting the daily need for urban water is considered. Much more attention needs to be given to forecasting methods if utilities are to make decisions that reflect the level of uncertainty precisely in future daily demand forecasts. Daily water consumption, unlike annual and monthly water consumption, is much more highly dependent on chance. Goal. The main goal of this paper is to obtain enough accurate forecasts of daily urban water consumption. Method. An algorithm for calculating the urban daily water demand forecast based on the concept of same-type days of water demand for previous years has been suggested. Scientific novelty. The originality of the method lies in the fact that it does not use neural network models, but still makes it possible to obtain enough accurate forecasts of daily urban water needs. Results. The presented algorithm for calculating the urban daily water demand forecast has been implemented in the form of a software package and has been tested for many years in real-life conditions. The average absolute percentage error of the daily forecast of urban water demand for one month does not exceed 5 %. Practical significance. The practical value of this work lies in the fact that the presented software complex for calculating the forecast of the city's daily water demand can be used in the information services of city utility companies to make operational and tactical decisions regarding the provision of water supply services to the population.ukforecastingforecasttime seriesmodelartificial neural networkwater demandwater supplystatistical analysisArticle004.9410.30977/BUL.2219-5548.2023.100.0.30