Download presentation

Presentation is loading. Please wait.

Published bySebastian Meyer Modified over 4 years ago

1
Terms of Reference 1. F ocus on illustrating how statistical methods are used to solve business problems and how statisticians interact with colleagues and clients to achieve this. 2. Descriptions of past and on-going case studies 3. Short introductions to their organisations and to the diverse roles of the organisations statisticians, Models Historic Basics WEATHER from Met Office (Actual and forecast)

2
Reading University RSS 15th June 2005 Shanti Majithia Forecasting Development Manager Wokingham, Berks UK Transmission

3
Agenda My Background Company Background Application of Statistical techniques within the Company University and Project work Conclusion

4
My Background Further education in London Maths Stats and Computing Market Electricity Load research, Manpower planning Operational Forecasting (Short Time Scale) Liaison with students and Uni. to assist in data and direction Presentations: Research paper and Forecasting conferences Wind Energy, Climate Change, Heating and Cooling Load ( Air Con) Risk management Short term Gas Demand and Supply Forecasting Translating data, analysis and information into decision making tools

5
Argentina: 27.6% Transener Zambia: 38.6% CEC (Copperbelt transmission) Australia: Basslink (Interconnector to Tasmania) UK: E&W transmission GB Gas Transportation LNG GridCom USA: NEESCom National Grid Transco - principal activities in regulated electricity and gas industries

6
Over 21,000 Transmission Towers Over 13,000 circuit km of 400 & 275kv transmission lines and cables Fibre optics National Grid - UK : Electricity 300 substations

7
Electricity Balance generation and demand efficiently Ensure quality and security Non stop process Keeping the lights on

8
Electricity Transmission Elements 96/29355 ISSUE A SH. 1 OF 1 30-04-99 Power Station Generator Transformer 33 kV To Small Factories, Farms, Residential Areas and Schools Large Factories, Heavy Industry Medium Factories, Light Industry 11 kV240 V 132kV 23kV400kV }

9
40 % of Distribution TRANSCO & IPGTS TRANSCO Suppliers Producers DFOS Storage Operators Shippers Traders The UK Gas Industry Model CompetitiveMonopoly Energy CompaniesRegulated Systems Gas supplyIndependent transmission

10
Gas: National Transmission System (NTS) 6,600km 450-1220mm diameter pipeline High strength steel X65-X80 Operating pressure design 70-94bar 7 Transco terminals 24 compressor stations 400 above ground installations (AGI) Key Stats Max demand 02/03 205 GW Peak Demand (1/20) 240 GW Energy Supplied 1150 TWh/yr

11
Compressor Salt cavity storage LNG storage LDZ Offtake Regulator Station Governor High pressure storage Low pressure storage Industry Terminal Power Station Gas: From Beach To Meter

12
Balance supply and demand efficiently Balance supply and demand efficiently Facilitate the market Facilitate the market Ensure quality and security Ensure quality and security Maximise system capacity Maximise system capacity Non stop processes Non stop processesBUT Gas can be stored => daily balancing Gas can be stored => daily balancing Electricity cant => real-time balancing Electricity cant => real-time balancing Real Time System Operation in Gas and Electricity…..

13
Application of Statistical Techniques within NGT Data collection - live metering, market intelligence and field measurement Data mining e.g. Kohonen SOMs, Genetic Algorithms. Forecasting Methods Regression, Box-Jenkins, Bayesian, Neural Network (MLP & ALN), Curve fitting and Holts-Winters, Arch and Garch Probability and Risk Management Liaison to keep abreast of modern methods e.g. Statistical methods Management Information System

14
Area of Application of Statistical Techniques Forecasting Energy Demand Trading advice Minimising of volatility Management of probability and risk Calculating and calibrating climate sensitivity Health of the assets in terms of the return period Simple use of statistical methods in plant reliability Responses on the efficiency of the equipment

15
Electricity Forecasting Techniques Multiple linear regression Last 3 years of historic data Summer (BST) and winter (GMT) Weekdays / Sat / Sun Special days excluded Conventional and Trend models ~ 120 models per annum Interpolation between cardinal points for half hourly resolution

16
Forecasting Tools Oracle database Weather and demand feeds StatGraphics EViews SAS PREDICT & Forecaster Clementine NN and ALN Genetic Algorithm Library (MIT)

17
Weather Input Historical Demand Input Mathematical & Statistical Models The Forecast The Forecasting Process

18
Demand - Influences Seasons/ Weather Exceptional events TV Typical Summer Day Minimum Summer Day Typical Winter Day Maximum Winter Day GW

20
The Effect of Temperature on Demand 0 1000 2000 3000 4000 5000 6000 7000 0 1 234 5 6 78 9 101112131415161718192021222324252627282930 Temperature Demand Effect (MW) COLD High Demand Comfortable HOT High Demand Degrees Centigrade

21
The Effect of Illumination on Demand 0 500 1000 1500 2000 2500 3000 3500 4000 4500 05101520253035404550556065707580859095100105110115120125130135140145150155160 Logarithmic Function of Illumination Demand Effect (MW) DULL High Demand BRIGHT Low Demand

22
Four Weather Variables Average Temperature [TO]: average of 4 spot hourly temperatures up to current hour Effective Temperature [TE]: TO lagged to 50% with TE from 24 hours previous Cooling Power of the Wind [CP]: empirical combination of temperature and wind speed Effective Illumination of the Sky [EI]: (EI=MI-ID), where ID is a function of visibility, numbers and types of cloud layers and amounts of precipitation and MI is maximum illumination. In the logarithmic domain.

23
Winter Week Day Peak Demand Modelling Multiple Regression Model Of Demand Weekday Darkness Peak Demand = + Weather Dependant Demand + Day of Week An econometric regression model of the weekday darkness peak is determined on the four previous winters demand & weather data + Seasonal trends + error terms The days affected by Christmas & New Year holidays are excluded from the sample Mean Darkness Peak Demand

24
Weather Dependant Demand Weather Dependant Demand function TE t + 2 TE t 2 + EI t + CP t

26
Example of a Weather forecast data

27
Gas Forecasting - suite of models using different techniques Profile (ARIMA) STF (Complex regression) Neural network ALN (Adaptive logic network) Inday (Simple regression) Bayes (Complex regression) Box 1 (Box Jenkins) Box 2 (Box Jenkins) Sumest (Complex regression) Wintest (Complex regression) D-1 Average weighted according to performance over last 7 days (Combination). Further adjustment made based on recent combination error (CAM) D D D D D

28
What Does a Gas Model Look Like? PROFILE – WITHIN DAY MODEL PROFILE model uses the Box Jenkins technique to forecast within day gas demand. There are two different models in the program. Model 1 is usually used for the 10am forecast and model 2 for the rest of the day. However, if the 9am temperature is greater than either the 1pm or 3pm temperature then model 1 is used for the 1pm and 4pm forecasts. Model 1 (at hour k) (used for 10:00 forecast) 7 D t (h) = w 0 7 T t (3) + w 1 7 T t (6) + w 2 7 T t (9) + w 3 7 D t (k) + (1- 1 B) (1- 7 B 7 ) a t Model 2 (at hour k) (used for forecasts at other times) 7 D t (h) = w 0 7 T t (h-1) + w 1 7 D t (6) + w 2 1 k 7 D t (j) + (1- 1 B) (1 - 7 B 7 )a t whereT t (h) is the temperature at hour h on day t, D t (h) is the corresponding hourly demand on day t, a t is the error in the forecast demand for hour h on day t, B is the backward shift operator i.e. By t = y t-1 w 0, w 1, w 2, w 3, 1, 7 are model parameters.. PROFILE model uses the Box Jenkins technique to forecast within day gas demand. There are two different models in the program. Model 1 is usually used for the 10am forecast and model 2 for the rest of the day. However, if the 9am temperature is greater than either the 1pm or 3pm temperature then model 1 is used for the 1pm and 4pm forecasts. Model 1 (at hour k) (used for 10:00 forecast) 7 D t (h) = w 0 7 T t (3) + w 1 7 T t (6) + w 2 7 T t (9) + w 3 7 D t (k) + (1- 1 B) (1- 7 B 7 ) a t Model 2 (at hour k) (used for forecasts at other times) 7 D t (h) = w 0 7 T t (h-1) + w 1 7 D t (6) + w 2 1 k 7 D t (j) + (1- 1 B) (1 - 7 B 7 )a t whereT t (h) is the temperature at hour h on day t, D t (h) is the corresponding hourly demand on day t, a t is the error in the forecast demand for hour h on day t, B is the backward shift operator i.e. By t = y t-1 w 0, w 1, w 2, w 3, 1, 7 are model parameters..

29
NTS Supply Forecasting Model types Every supply point End of d ay Within day Regression of DFNs & AT-Link noms Every hour WhenForWhatHorizonHow - Model type Nat End of d ay Within day Regression of DFNs & AT-Link noms Every hour Every supply point End of d ay Day ahead Regression of change of supply Every hour Every supply point Every hour 7 days ahead Holts-Winters (Time series) Once per day

30
What is a Holts-Winters Model?

31
Understanding Data Questions What to look for in the data before preparing forecasts How to treat data when problems are recognised How to prepare forecasts using different models and techniques When each forecasting model is appropriate How to use forecasts effectively after they are prepared

32
Why is a forecast needed? Who will use the forecast, and what are their specific requirements? What level of detail or aggregation is required and what is the proper time horizon? How accurate can we expect the forecast to be? Will the forecast be made in time to help decision making process? Does the forecaster clearly understand how the forecast will be used in the organisation? Key Questions

33
Projects and Case Studies The seasonal forecast of electricity demand: a simple Bayesian model with climatological weather generator Sergio Pezzulli, Patrizio Frederic, Shanti Majithia,

34
Coloured areas are clusters, each with a distinctive daily demand profile. Red text is their interpretation. Data mining --- Clustering of Electricity Profiles

35
Clustering of Gas Profiles Kohonen Network (SOM) Analysis Yellow-ish areas indicate similar profiles, Red-ish areas indicate more varying profiles. Jan & Dec Jan Feb Mar & Nov Apr May & Oct June July Aug & Sept

36
North Thames LDZ, Early Jan 2003

37
New up coming Challenges Windpower Variable Uncertain Uncertain uncertainty Danger: possibility of sudden loss Weather differences can be at finer geographic resolution

38
Volatility and Uncertainty How best to model? Ensemble forecasts? How to make operational decisions?

39
Site Clustering Site clustering can be used to produce a more accurate national prediction by taking local conditions into account The main way of achieving this is to have a reference farm which is representative of the cluster It is possible to then use cluster predictions as inputs to a national model or simply upscaled One further thought is to forecast both a reference farm and a cluster separately and use them to create a more stable regional prediction

40
Daily Load Forecasting using ARIMA-GARCH and Extreme Value Theory University of Loughborough EPSRC Project

41
Application Climate Change Impacts on Electricity demand can be categorised into a long term (monthly) and short term (daily and hourly) load forecast. Long term load forecast using the multiple regression approach completed. The results are satisfactory. 80 years projection requires the UKCIP scenario and BESEECH data (population, GDP, consumer spending). Short term load forecast using Box Jenkins and Extreme Value Theory is also completed. Waiting for hourly climate data from BADC and CRU before we can extend our daily/hourly projections to 2080s.

42
ARIMA (p, d, q) Model The AutoRegressive Integrated Moving Average (ARIMA) model is a broadening of the class of ARMA models to include differencing. Reason: daily and hourly pattern are volatile and shows a strong seasonal pattern. p: no. of autoregressive terms, d: the number of non-seasonal differences and q = no of lagged forecast errors in the prediction equation. ARIMA(1,1,1) is used

43
Probability Distributions n t is a standardized, independence, identically distributed (iid) random draw from some probability distributions. 3 distributions are used for this purpose:- a) Normal b) Student-t c) Extreme Value Distribution For quantiles > 0.95, extreme value distribution is used.

44
Example of Scenario Forecasting (with max and min scenarios)

45
Combination of Distribution-- Example Link between Annual Peak and Weekly Peak The density traces shows how the median of the simulated winter peak distribution cuts off an area of about 12% on the corresponding distribution of simulated weekly peak demands. Winter ACS Median 12% Area cut off Weekly Peak Distribution

46
Probability Distribution

47
Conclusions Various statistical applications demonstrated Wide variety of Statistical method used in data rich Energy business Opportunity for Statistician/Business Analysis

Similar presentations

OK

Sales Forecasting using Dynamic Bayesian Networks Steve Djajasaputra SNN Nijmegen The Netherlands.

Sales Forecasting using Dynamic Bayesian Networks Steve Djajasaputra SNN Nijmegen The Netherlands.

© 2018 SlidePlayer.com Inc.

All rights reserved.

To make this website work, we log user data and share it with processors. To use this website, you must agree to our Privacy Policy, including cookie policy.

Ads by Google