Reduce Operating Costs

with Predictive Energy Analytics

Reduce Operating Costs

Using Predictive Energy Analytics, the primary goal of the project was to provide the operators with real-time, on-demand energy information to reduce operating costs.

Situation

Energy cost mitigation at a California wastewater facility was extremely difficult. Many factors were outside the control of plant personnel, including the dynamics of wastewater flow, energy sources, and the requirements of integrating effluent from multiple municipal agency treatment facilities at various levels of water treatment. Dissimilar data collection platforms and "raw data only" reporting compounded the issue.

Stop Modeling Energy With Excel!

PredictEnergy® will model all of your energy usage for you.

Goals and Objectives

the process to reduce operational costs

The primary goal of the project was to provide the operators with real-time, on demand predictive energy analytics data from their energy sources. This helps plant operators reduce operating expenses and assess power quality because it enables energy management procedures.

The steps to accomplish this goal were:

  • Capture real-time energy and process data.
  • Integrate with onsite distributed energy generation (solar photovoltaic PV) and co-generation from digester gas).
  • Perform predictive energy analytics to provide the operators with immediate feedback for capacity and energy requirements.

An additional goal was to quantify energy cost allocation based on utility tariff schedule pump processing.

Lesson

Existing SCADA and metering onsite was insufficient to collect the required data in a cost-effective, timely and efficient manner. To provide the level of analytics needed, PredictEnergy® scales and manages data by capturing and developing historical, current and predictive energy from the utility and distributed energy sources. PredictEnergy® manages this information to incorporate the business context. The client's business and waste management process conditions predictive analysis. These are the key elements which impact the energy cost equation.

predictive energy analytics to reduce operational costs

Energy and flow data were installed at key points including main power meter, specific load centers representing the process, PV inverter output, co-gen output, weather station, and SCADA interface. Where PredictEnergy® processes real-time data. The data acquisition process inputs analytics using a series of facilitated requirement session which allows operators to identify and visualize key inputs. Energy sources (utility, cogen, and solar PV) are paired against energy uses (facility process and member agency facility pumping). Energy analytics used utility tariff analysis to calculate real-time energy costs for pumping and processing. Along with optimizing co-gen energy cost off-set and quantify the cost avoidance provided by the solar PV.

The Results

Analytics identify opportunities for the operator to shift process loads and energy source usage to minimize both operational expense and energy costs. Operational cost reduction exceeded 15% due to significant cost savings as compared to the nominal cost of PredictEnergy®. That's an astounding simple payback of less than one year was realized!

Additionally, the operators gained the ability to quantify their service to the other wastewater facilities in the form of real-time flow rate, pumping energy usage and pumping energy costs. This effectively provided feedback to these facilities which eliminated operator man hours for manual raw data collection, utility bill review and evaluation, and usage estimation. Each of the other four facilities gained the potential for their own energy cost savings.

The facility continues to gain operational cost reduction using the homogenized data collection and their predictive analytics toolset.

Pin It on Pinterest

Share This