Using Data-Driven Analytics for SMART CSO Management

Using Data-Driven Analytics for SMART CSO ManagementAbstractThis paper presents a smart combined sewer overflow (CSO) monitoring and control project in Wilmington, Delaware. The audience will learn about how an innovative integrated Collection System Toolbox can assist utilities to modernize their CSO infrastructure by increasing level and flow monitoring, coupled with optimization and automation in order to maximize flow to treatment plant and reducing CSOs. In 2020, Jacobs began operating the City of Wilmington's wastewater treatment system, which includes the wastewater treatment plant (WWTP), the CSO control facilities, and the wastewater pump stations. Previously, only 6 out of the 41 CSOs have level and/or flow monitoring, and those are part of a real time control system that is operated separately from the WWTP and the rest of the CSOs. The remaining 35 CSOs did not have monitors, so a crew of four visits each CSO at least three days a week, which requires much drive time and traffic control, risking worker safety. The CSO monitoring project was developed to add level monitors at the 35 unmonitored CSOs as well as flow meters on three previously unmetered interceptors and integrate them with the existing monitoring system into a state-of-the-art intelligent operations platform. The City of Wilmington and Jacobs received a grant from Cisco Systems to install a radio mesh to communicate between the remote sensors and a low-power wide area network (LoRaWAN) system. The LoRaWAN system transmits the data from remote sensors back into the WWTP supervisory control and data acquisition (SCADA) system. Therefore, the CSOs and the WWTP are on the same SCADA system, enabling additional cyber security features for the remote sensors. The intelligent operations platform monitors the collection system and facilities in real time and generates alerts based on data analytics. Instead of inspecting 35 CSOs three times per week, the system generates an alert to the maintenance team to inspect a CSO only when needed. This exponentially decreases risks to worker safety and increases their effectiveness at reducing CSOs and preventing dry weather overflows and sanitary sewer overflows. The platform also uses machine learning and artificial intelligence to predict the behavior of the system, which enables operators to see when a wet-weather CSO event is imminent in the future and use this new insight to make operational decisions at pump stations and the WWTP. Additionally, Wilmington and other utilities have real time control (RTC) facilities to optimize their operational goals and minimize pollution or costs. Using wastewater collection systems with CSO facilities as an example, RTCs are built to maximize storage and treatment of combined sewage during wet weather and minimize untreated sewer overflow volumes and frequencies that pollute the waterbodies, that typically operate on manually adjustable setpoints. Wilmington has often operated their RTCs and terminal pump station in reaction to the conditions at the WWTP, which receives flow from both the City of Wilmington and surrounding New Castle County. The City or the WWTP operators cannot control the County's system or the flow coming to the WWTP from the County. Oftentimes, the City's terminal pump station is ramped down during a rain event to prevent spills at the WWTP in response to the County flow, which leads to CSOs in the City's system. Once the data were being collected, they were integrated along with rain gauges, RTC facility and pump station SCADA data, tide gauges, tide forecasts, and weather forecasts onto one platform called Aqua DNA. With Aqua DNA, machine learning was applied as data were collected in real-time to learn the behavior of the system, developing a 'baseline' level at the CSOs. Alerts were then developed for 'off baseline' as well as if data transmission stopped or if overflows were occurring. The 'eyes on the system' dashboard, shown in Figure 1, provides a view of the severity of the alerts on a GIS map that allows the CSO crew to know where their biggest issues are occurring in real-time. RESULTS AND CONCLUSIONS The system has been fully functional with all level and flow sensors since July 2023. The team have continued to refine the alerts based on the input from the CSO crew. The main refinements have been made to ensure that the alerts are not too frequent or too sensitive. Based on the alerts, the CSO crew will go from at least three days a week in the field to one day a week in the field by January 2024. The reduced driving time and traffic control will not only increase the safety of the team members but also give the team time to perform preventative maintenance that they may not otherwise be able to do. With the 'eyes on the system', the City of Wilmington is also able to meet the requirements of their Long-Term Control Plan to monitor the CSOs. Additionally, they will have more accurate CSO volume estimates using the level sensor data, since the 35 previously unmonitored CSOs used hydraulic modeling results to estimate CSO volume. Additionally, the hydraulic model has been calibrated using past data. The real-time data are being used with the autocalibration module to provide near real-time calibration of the hydraulic model. Additionally, the optimization module is set up to run rainfall forecasts, especially for smaller and medium-level storms, to optimize setpoints at the RTCs and pump stations to maximize flow to treatment and minimize upstream SSOs and downstream CSOs. Figure 2 shows how the tool is set up to run the model based on predicted rainfall. The solution has integrated the hydraulic model to estimate flows from the City with a data-driven model to estimate flows from the County (see Figure 3). By combining these estimates, decisions can be made to optimize operations ahead of the storm, including making sure that the City's terminal pump station is pumping at full capacity for as long as possible. Additionally, running the model allows for the operators to see how each CSO will react to the impending storm, even showing where levels might increase after the storm is over (see Figure 4). In conclusion, the 'eyes on the system' dashboard with alerts tailored to the CSO crews pain points has informed the City and the CSO crew of potential problem areas that were not previously known and helped to reduce the drive time and traffic control. The CSO crew are now able to be proactive in their maintenance, rather than reactive. The combination of the hydraulic model and data-driven models have allowed the WWTP operators to know what flow may be headed their way ahead of the storm. Decisions can now be made to maximize treatment and minimize SSOs and CSOs by reviewing the results holistically.This paper was presented at the WEF Collection Systems and Stormwater Conference, April 9-12, 2024.SpeakerHill, LiiePresentation time11:15:0011:45:00Session time10:45:0011:45:00SessionSmart Collection System ToolsSession number17Session locationConnecticut Convention Center, Hartford, ConnecticutTopicArtificial Intelligence, Coastal Systems, Combined Sewer Overflow, Digital Twin, Flow Projections, GIS, Machine Learning, Predictive AnalyticsTopicArtificial Intelligence, Coastal Systems, Combined Sewer Overflow, Digital Twin, Flow Projections, GIS, Machine Learning, Predictive AnalyticsAuthor(s)Hill, LiieAuthor(s)L. Hill1, S. Liu1, J. Baldwin1Author affiliation(s)Jacobs 1SourceProceedings of the Water Environment FederationDocument typeConference PaperPublisherWater Environment FederationPrint publication date Apr 2024DOI10.2175/193864718825159393Volume / Issue Content sourceCollection Systems and Stormwater ConferenceCopyright2024Word count8