Weather Input Advancements in DemandWatch V5.0 Bring More Accurate Water Demand Forecasting Results to Users
New Version Delivers Accurate Forecast of Short-Term Water Demands for Near-Optimal Real-Time Control of Water Networks plus Anomaly Detection
Broomfield, Colorado, USA, — Expanding the boundaries of smart water network innovation, Innovyze, a leading global innovator of business analytics software and technologies for smart wet infrastructure, today announced the worldwide release of the V5.0 Generation of its DemandWatch for accurate and reliable water demand forecasts.
The new release expands the ability of water utilities worldwide to effectively leverage historical demand data to estimate future water demands for near-optimal real-time control and management of their water distribution systems under varying weather conditions. The software’s primary strength lies in its adaptive demand forecasting process, which can continually update and refine estimated demand values in real time. Armed with this power, water utilities can better plan, operate and manage their water distribution systems; improve conservation measures and anomaly detection; minimize energy consumption; meet regulatory compliance; and enhance customer service.
Water distribution network modeling is the most effective and viable way of predicting system behavior to solve a variety of design, operational and water quality problems. One critical tool for ensuring reliable network model predictions is the accurate estimation of short-term (e.g., daily) water demands. DemandWatch is expressly designed to give water utilities accurate water demand forecasts for their distribution network models. By helping utility planners and managers understand spatial and temporal patterns of water use these models can aid in optimizing system operations and capital planning.
“DemandWatch was successfully used by Optimise (a joint venture between J Murphy and Sons, Barhale Construction plc, Clancy Docwra Ltd and MWH Ltd) to help identify anomalous demand patterns in south London, UK,” said Christopher M. Bros, Project Manager for MWH UK Ltd. “We trained DemandWatch on historic data and used autoregression forecasting to locate potential bursts, background leakage rises and boundary breaches in DMAs (District Metered Areas). Its ability to accurately forecast short-term (24-48 hours ahead) helped our engineers differentiate data noise from underlying trends, improving our ability to guide the leak location activities of on-site teams.”
Added Bros: “DemandWatch’s predictor had to cope with varying night demand patterns through winter New Year celebrations and spring holiday periods, including city centre locations such as the iconic London Eye and suburban districts. Leakage monitoring uses 15-minute real-time data, and I was extremely impressed withDemandWatch’s accuracy in matching such short interval patterns and correctly predicting night flow usage for the subsequent 24-hour period.”
Designed for real-time applications, DemandWatch analyzes patterns from historical demand data and uses a powerful combination of Fourier transform and time-series autoregression modeling to accurately predict short-term (e.g., 24 or 48 hours) water demands. These patterns are used to identify both seasonal and weekly periodicities in daily water demands and daily periodicities in hourly water demands. A sequential fitting of terms is automatically generated to reveal patterns between days and hourly patterns within days. Fourier transforms are used to find daily cyclical patterns. Autoregressive terms add a “short-term memory” to fine tune daily and hourly predictions, greatly increasing the accuracy of forecasted values.
DemandWatch generates water demand forecasts at hourly intervals or at finer user-defined resolutions. Innovyze IWLive can readily use the output to perform accurate simulations that reliably predict network operational performance over the next few hours or days. The results of these simulations can then be used to achieve optimal operation and management of water distribution systems and detect real-time anomalies.
Extremely powerful and flexible, DemandWatch can also assist engineers in configuring and calibrating network models, aided by graphs and other reporting tools. Its adaptive learning process enables it to continuously generate predictions, taking observations from the recent past and predicting demand for the near future. Even if there is a loss of observed telemetry data, DemandWatch can still generate predictions from cyclical components of the model.
Easy to learn and use, DemandWatch is available as a stand-alone program that runs on nearly any computer or as a complementary module of IWLive. It can be installed, up and running in just a few minutes on a utility’s local computer. DemandWatch results can easily be integrated with other Innovyze smart water network solutions including InfoWater and InfoWorks WS.
Support for weather conditions is a key feature of the new release. DemandWatch can now take into account unexpected temperature changes, especially important during unusually hot summer days. Temperature data is optional; if no historical weather data or weather forecasts are available, DemandWatch will still compute a prediction for future demand. The software can model the effect of unexpected temperature changes on daily demand by taking the difference between the temperature forecast and the historical average temperature for that particular season, multiplying it by a regression factor, and adding it to the predicted daily demand. If the weather forecast is hotter than average, the predicted demand will be increased.
“Accurate short-term water demand pattern forecasting is essential for cost-effective operation and proper risk management of distribution systems,” said Paul F. Boulos, Ph.D., BCEEM, NAE, Hon.D.WRE, Dist.D.NE, F.ASCE, President, COO and Chief Technical Officer of Innovyze. “DemandWatch is an invaluable planning and operational tool for smart water networks, helping water utilities evaluate the relative impact of different management decisions and detect network anomalies. It also helps operators avoid implementing suboptimal operational control schemes. The new version exemplifies our ongoing commitment to delivering superior value to our customers who manage, operate and sustain safe, reliable drinking water distribution systems.”