Full Description

This powerpoint presentation focuses onshort-term consumption forecasting (STCF)techniques for energy management(AwwaRF Project #3066Water Consumption Forecasting toImprove Energy Efficiency of Pumping Operations). The first section of the presentation outlines short-termconsumptionforecasting -a key strategy tominimizeincreasing energycosts and includes these topics: operating costs for 19 sampled waterutilities in the 2003 AwwaRF Project; Electric Costs Rising Dramatically Due toIncreasing Fuel Costs; Other Factors Pushing Up ElectricEnergy Cost; Water Utility Responses to Rising Costs; Short Term Consumption Forecasting (STCF)Initiates Optimized Operational PumpScheduling Through an Energy Forecasting Consumption Moves WaterUtility from Reactive to ProactiveOperations Using an EWQMS; Pumping Operations are TypicallyConsumption-Following; STCF's Objective: Predict Hourly Consumptionfor Multiple Areas in the System and Move Waterfrom Source to Customer at Lowest Cost; STCF Enables Time Value Purchasingand Selling Energy - A Supply andDemand Strategy; STCF Window (Daily and Hourly)Depends on Application; Time-of-Use Pumping StrategyBased on a Forecast; Example of Time-of-Use, Demand, andEfficiency Strategies; STCF Enables SignificantWater Supply Opportunities; and, Scheduling Treatment Plant and Import WaterProduction Schedules Based on Short TermForecasting has Saved San Diego $Millions. The second part of the presentation provides a description and theresults of the AwwaRFProject #3066,"Water ConsumptionForecasting toImprove EnergyEfficiency ofPumping Operations" and provides an overview of the project and participating facilities. The four steps of the forecasting project include: Research Existing ForecastingTechniques Used at Water,Gas, and Electric Utilities; Analyze Operational Resultsat Four Water Utilities UsingSTCFs; Develop and Test PrototypeSTCFs Under OperatingConditions at Five Water Utilities; and, Analyze Data andPublish Results. The third part of the presentation provides conclusions and lessons learned: accuracy is highly dependent on quality ofhistorical data;other than temperature and rainfall, weathermay not be as important as one would think;retraining an ANN may degrade themodel;ANN models hold up well over time;Training ANN models with a full year of dataprovides better results than training with onlya single season of data; daylight savings is problematic for allforecast models;large number of input parameters can makemodels less responsive and more difficult tomaintain; Forecast is limited by accuracy ofmeasurement equipment; and,a short-term consumption forecaster "enables"proactive system operations to savesubstantial energy and other operating costs.

Product Details

Edition: Vol. - No. Published: 06/01/2007 Number of Pages: 38File Size: 1 file , 11 MB