Presentation on theme: "Data Analytics at American Electric Power"— Presentation transcript:
1 Data Analytics at American Electric Power Presentation to:SWEDEMay 8, 2014Tom Weaver, PE
2 Business Analytics is the convergence of three key areas OpportunitiesWorking with OpCos, define business opportunities or problems we are trying to solve in 3 areasDistributionMeterConsumerTechnical SolutionsDefine the technical solutions that meet business needs forData captureData storageComplex processingVisualizationAEP BusinessSolutionCommercialSolutionsDefine the commercial relationships that are required to make this journey successfulBuild vs. BuyCollaboration with othersCollaboration is vital as considerations are inter-connected
3 Degree of Intelligence (Competitive Advantage) Analytic Capabilities What does Business Analytics Mean?Standard ReportsAd Hoc ReportsQuery DrilldownAlertsStatistical AnalysisForecastingPredictive ModelingOptimizationDegree of Intelligence(Competitive Advantage)Analytic CapabilitiesAnalytic CapabilityAnswers the QuestionsStandard ReportsWhat happened?When did it happen?Ad Hoc ReportsHow many?How often?Where?Query DrilldownOr OLAPWhere exactly is the problem?How to I find the answers?Alerts/MonitoringWhen should I react?What actions are needed now?Statistical AnalysisWhy is this happening?What opportunities am I missing?ForecastingWhat if the trends continue?How much is needed?When will it be needed?Predictive ModelingWhat will happen next?How will it affect my business?OptimizationHow do we do things better?What is the best decision for a complex problem?
4 Metering Analytics Needs Analytics framework todayStarted simplepending maturity of vendor solutions–Conceptual ViewOPERATIONALMetering Analytics NeedsAnalytic CapabilityAvailability of Data for Load Research and Development of Detection Reports (Hot Sockets, Etc)StandardService Order ProcessingProcess/System MonitoringGUI for the integration of meter events and ordersAMI(UIQ&LGCC)SASMDMMACSS(MCS&OPS)TERSOperationalSWAMIData StoreDA System(PI)AATDCERAMIGOPowerOnUOSCES DataPEV DataPeopleSoftGIS
5 Why is Data Analytics a Strategic Initiative for the Industry? SenseCommunicateComputeControlPower PlantsTransmissionSubstationsDistributionConsumersSensor and Communication Technology Leapfrogging Ability to Mine Data for High Value Applications for Electric Utilities5
6 Distribution Modernization Demonstration on “Big Data” Data Management & Analytics to Support Operations, Planning and Asset ManagementMission:Benchmark “State of the Industry”Demonstrate applicationsCollaborate with industry leadersVision:Develop “best practices”Accelerate understandingDocument cost benefitPotential Breakthroughs:Better visualizations, insightsEmerging analytics capabilitiesApplication of dataTake advantage of new opportunities afforded by a sensor enabled grid
7 Data Integration and Analytics Applied to a Storm Event and Recovery Day –(3) Storm ForecastDay (0) Storm EventDay (+3) Storm RecoveryLeverage the New EPRI High Performance Computing SystemDefine the right system for the applicationEvaluate fast pattern recognition for storm damage dataData Sets:Weather ForecastsHistorical DamagePredictive AnalyticsStorm Protection SettingsManagement SystemsSituational AnalyticsAssets and InventoryField Crew Interfaces1 0 1Field Crew SupportCustomers InterfacesAMI, SCADA, GISHigh Performance Computing RequirementsDamage AssessmentsN+1 Data Sources
8 AMI Meter Temperature Monitoring Monitoring 502,310 meters.85% accurate, 520 Issues out of 612 Field Orders.Next Steps for on-going Improvements:Automate monitoring.Change cutoff per season for more accuracy.Optimize parameters?
10 Site Genie/Quality of Service Report Use SAS to decode then analyze the vectors.Broken CT and PT on transformer rated meters, poor connections under billing of commercial customers.New customer validation of service, saved Ohio 208 site visits this year.IssuesPopulationOhio385,7760.66%PSO191,7181.11%I&M473
11 Voltage Magnitude Analysis – Transformer Rated Meters Next Step: Create automated programs to analyze.Description of IssueNumberCorrected Service Type in Meter8Bad Cable2Service Incorrect in MACSSBad PTBlown Transformer Fuse1TheftNo IssuesTotal Feedback17
12 FUTURE: Energy Diversion Detection – Monitor Load Profile Analyze the Voltage and kWh of Load ProfileFlag premises with high voltage drop but low kWh compared to neighbors.Program flagging premises documented on the wrong transformer.
13 FIRST: Clean Up AEP’s MACSS Data – Correlate Premises to Proper Transformer 2179South
14 Texas Voltage Magnitude Monitoring 2S on 12S Service: 75% registrationHi Volt/Failing Transformers – 111 found Oct. ’13 to Feb. ‘14
15 Utilities looking for . . . Improving grid reliability Grid Hardening Optimize Utilization & CostsImprove grid efficiencySpeed up RestorationLimit the ImpactAvoid the OutageGrid HardeningGrid ResiliencyGridRestorationGridUtilizationGridHealthImproving grid reliabilityUsed with permission fromGeneral Electric
16 Typical grid reliability objectives Total Grid Risk ManagementProactive service & maintenanceReduction of capital expensesLower repair costsEnhance system reliability, availability & performanceSupport optimized asset replacementOptimize workforce productivity & safetyUsed with permission fromGeneral ElectricFocused maintenanceReduced CapEx, OpExEnhanced PerformanceManage asset risksEfficient & Optimized OperationsProactive asset risk management across entire life cycleUsed with permission fromGeneral Electric16
17 AEP Distribution Analytics Currently planningLoad analyticsVegetation managementConvert sensor data to actionable stepsFuture PlansAutomating reliability metricsTying asset age and health to outage trendsStorm damage prediction
18 Tom Weaver – firstname.lastname@example.org Questions?Tom Weaver –