Deep learning with long short-term memory neural networks combining wavelet transform and principal component analysis for daily urban water demand forecasting
B Du, Q Zhou, J Guo, S Guo, L Wang - Expert Systems with Applications, 2021 - Elsevier
… and catching the peaks in time series, … daily water demand data are collected from 1st
January 2016 to 11th September 2020, with the first 998 daily data are used for training the model …
January 2016 to 11th September 2020, with the first 998 daily data are used for training the model …
Hybridised artificial neural network model with slime mould algorithm: a novel methodology for prediction of urban stochastic water demand
SL Zubaidi, IH Abdulkareem, KS Hashim… - Water, 2020 - mdpi.com
… the correlation coefficient between water consumption and maximum temperature time series
(from 0.63 to 0.93). Additionally, the correlation coefficient between the stochastic signal of …
(from 0.63 to 0.93). Additionally, the correlation coefficient between the stochastic signal of …
Smart meters data for modeling and forecasting water demand at the user-level
… reported cumulative values of water consumption, generating misleading peaks. These outliers
… This study uses a feed forward neural network with input, hidden, and output layers. The …
… This study uses a feed forward neural network with input, hidden, and output layers. The …
Hourly and daily urban water demand predictions using a long short-term memory based model
L Mu, F Zheng, R Tao, Q Zhang… - Journal of Water …, 2020 - ascelibrary.org
… of models are available for urban water demand forecasts … These include artificial neural
networks (ANNs) that have been … RF models, especially when the daily maximum temperature ( …
networks (ANNs) that have been … RF models, especially when the daily maximum temperature ( …
A two-layer water demand prediction system in urban areas based on micro-services and LSTM neural networks
… peak consumption or water leakage [5]. In deploying a smart … of the water consumption
prediction model using LSTM. While … for water consumption acquisition, water demand prediction, …
prediction model using LSTM. While … for water consumption acquisition, water demand prediction, …
A method for predicting long-term municipal water demands under climate change
… model was run several times to find the best neural network architecture to forecast municipal
water demand. … that maximum temperature, radiation and rain, are reliable predictors when …
water demand. … that maximum temperature, radiation and rain, are reliable predictors when …
Applying human mobility and water consumption data for short-term water demand forecasting using classical and machine learning models
K Smolak, B Kasieczka, W Fialkiewicz… - Urban Water …, 2020 - Taylor & Francis
… with water usage data is proposed. This study uses 51 days of water consumption readings
… To ensure maximum efficiency in data processing, a spatiotemporal database was created …
… To ensure maximum efficiency in data processing, a spatiotemporal database was created …
… strategy for efficient energy management with day-ahead demand response signal and energy consumption forecasting in smart grid using artificial neural network
… The pricebased DR programs include critical peak pricing scheme (CPPS), time of use … In
this section, the simulation results and discussion are presented to validate the performance of …
this section, the simulation results and discussion are presented to validate the performance of …
Hybrid ensemble intelligent model based on wavelet transform, swarm intelligence and artificial neural network for electricity demand forecasting
… From the descriptive statistics (see Table 6), the proposed model’s mean, standard deviation,
minimum and maximum values are almost the same as the actual data values than the …
minimum and maximum values are almost the same as the actual data values than the …
The prediction of municipal water demand in Iraq: a case study of Baghdad governorate
SL Zubaidi, H Al-Bugharbee… - … on Developments in …, 2019 - ieeexplore.ieee.org
… model doesn’t need any data pre-processing, and it outperforms the models of artificial
neural network … data reaches 0.92, and the maximum reaches 0.987 as shown in Figure 4. In …
neural network … data reaches 0.92, and the maximum reaches 0.987 as shown in Figure 4. In …