FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003
COMPLETE SPECIFICATION (See Section 10 and Rule 13)
Title of invention:
OPTIMIZATION FRAMEWORK FOR ELECTRICITY POWER PROCUREMENT PORTFOLIO IN PRESENCE OF FORECAST ERRORS
Applicant
Tata Consultancy Services Limited A company Incorporated in India under the Companies Act, 1956
Having address:
Nirmal Building, 9th floor,
Nariman point, Mumbai 400021,
Maharashtra, India
Preamble to the description
The following specification particularly describes the invention and the manner in which it is to be performed.

TECHNICAL FIELD
[001] The disclosure herein generally relates to electricity power procurement portfolio, and, more particularly, to an optimization framework for electricity power procurement portfolio in presence of forecast errors.
BACKGROUND
[002] Smart buildings/smart infrastructures are continually striving towards electricity conservation and electricity consumption management. With the deregulation of the electricity industry, most of the consumers enjoy the luxury of procuring electricity power/electricity from multiple sources such as utility retailer, generators (through contract), markets, or neighbors (peer-to-peer). With the availability of several choices for procurement of electricity power, there is a need to optimize across the available sources by deciding on the allocations for different options while considering the associated risks with each option. The optimization can be defined in terms of monetary cost, carbon footprint, or the overall risk and this process is referred to as portfolio optimization (PO).
[003] Traditionally, the problem of electricity power procurement has been largely addressed. However, the conventional electricity power procurement optimization models are available to buy and sell electricity power based on estimates/forecasting of demand/supply and market prices, wherein forecasting an estimate of demand/supply and market prices is error-prone and adversely impacts the portfolio allocations and savings/profits. While these existing techniques discuss methods to optimize electricity power procurement the risks introduced by the error in forecasting /estimating the demand/supply and market prices for optimization is mostly neglected.
SUMMARY
[004] Embodiments of the present disclosure present technological improvements as solutions to one or more of the above-mentioned technical

problems recognized by the inventors in conventional systems. For example, in one embodiment, a method for optimization framework for electricity power procurement portfolio in presence of forecast errors is provided. The method includes receiving a plurality of input parameters associated with electricity power procurement in power domain, the input parameters comprising of a plurality of historic data and a plurality of constraints, wherein the plurality of historic data comprises of a historical market price and a historical consumer demand, and the plurality of constraints comprises a captive generation information and a risk aversion coefficient. The method further includes forecasting through a time-series forecast modelling technique to obtain a demand forecast and a market price forecast based on the plurality of historic data. The method further includes computing a set of forecast errors, through an error computation technique using the plurality of historic data, the demand forecast and the market price forecast. The method further includes generating a risk model based on the set of forecast error and the plurality of historic data to obtain a risk estimate from the risk model through a variance-covariance technique. The method further includes generating a set of primary electricity power procurement parameters and optimizing the set of primary electricity power procurement parameters through a procure-optimization technique based on the plurality of constraints, the demand forecast, the market price forecast and the risk estimate. The method finally includes refining the set of primary electricity power procurement parameters, by the one or more hardware processors, to obtain a final electricity power procurement parameter through a refining technique using the demand forecast and the plurality of historic data.
[005] In another aspect, a system for optimization framework for electricity power procurement portfolio in presence of forecast errors is provided. The system includes a memory storing instructions, one or more communication interfaces; and one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to receive a plurality of input parameters associated with electricity power procurement in power domain, via a one or more hardware processors, the input parameters comprising of a plurality of historic data

and a plurality of constraints, wherein the plurality of historic data comprises of a historical market price and a historical consumer demand, and the plurality of constraints comprises a captive generation information and a risk aversion coefficient. The system is further configured to forecast, by the one or more hardware processors, through a time-series forecast modelling technique to obtain a demand forecast and a market price forecast based on the plurality of historic data. The system is further configured to compute a set of forecast errors, by the one or more hardware processors, through an error computation technique using the plurality of historic data, the demand forecast and the market price forecast. The system is further configured to generate a risk model, by the one or more hardware processors, based on the set of forecast error and the plurality of historic data to obtain a risk estimate from the risk model through a variance-covariance technique. The system is further configured to generate a set of primary electricity power procurement parameters and optimize the set of primary electricity power procurement parameters , by the one or more hardware processors, through a procure-optimization technique based on the plurality of constraints, the demand forecast, the market price forecast and the risk estimate. The system is further configured to refine the set of primary electricity power procurement parameters, by the one or more hardware processors, to obtain a final electricity power procurement parameter through a refining technique using the demand forecast and the plurality of historic data.
[006] In yet another aspect, a non-transitory computer readable medium for optimization framework for electricity power procurement portfolio in presence of forecast errors is provided. The program includes receiving a plurality of input parameters associated with electricity power procurement in power domain, the input parameters comprising of a plurality of historic data and a plurality of constraints, wherein the plurality of historic data comprises of a historical market price and a historical consumer demand, and the plurality of constraints comprises a captive generation information and a risk aversion coefficient. The program further includes forecasting through a time-series forecast modelling technique to obtain a demand forecast and a market price forecast based on the plurality of

historic data. The program further includes computing a set of forecast errors, through an error computation technique using the plurality of historic data, the demand forecast and the market price forecast. The program further includes generating a risk model based on the set of forecast error and the plurality of historic data to obtain a risk estimate from the risk model through a variance-covariance technique. The program further includes generating a set of primary electricity power procurement parameters and optimizing the set of primary electricity power procurement parameters through a procure-optimization technique based on the plurality of constraints, the demand forecast, the market price forecast and the risk estimate. The program finally includes refining the set of primary electricity power procurement parameters, by the one or more hardware processors, to obtain a final electricity power procurement parameter through a refining technique using the demand forecast and the plurality of historic data.
[007] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
BRIEF DESCRIPTION OF THE DRAWINGS
[008] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles:
[009] FIG. 1 illustrates an exemplary system of an optimization framework for electricity power procurement portfolio in presence of forecast errors according to some embodiments of the present disclosure.
[010] FIG. 2 is a functional block diagram of the optimization framework for electricity power procurement portfolio in presence of forecast errors according to some embodiments of the present disclosure.
[011] FIG.3A and FIG.3B is a flow diagram illustrating a method of optimization framework for electricity power procurement portfolio in presence of forecast errors, in accordance with some embodiments of the present disclosure.

[012] FIG.4 is a graph illustrating the plurality of historic data, in accordance with some embodiments of the present disclosure.
[013] FIG.5 is a graph illustrating a performance study of the optimization framework for electricity power procurement portfolio in presence of forecast errors against existing electricity power procurement portfolio techniques that include a default, an ideal portfolio optimization (PO) and a legacy PO.
DETAILED DESCRIPTION OF EMBODIMENTS
[014] Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the scope of the disclosed embodiments.
[015] Optimal power procurement helps electricity consumers save on their electricity costs. The conventional electricity power procurement portfolio refers to optimally procuring electricity power from across a plurality of sources while considering process variance risks such as estimates/forecasting of demand/supply and market prices. However, it is not only important to be cognizant of the process variance risks but also of the risks introduced due to the estimation errors. The method of present disclosure is an optimization framework for electricity power procurement portfolio in presence of forecast errors, which is an improvisation of the conventional power procurement optimization techniques as the disclosed method models a plurality of risks due to demand and market price forecast errors to be used for electricity power procurement portfolio.
[016] Referring now to the drawings, and more particularly to FIG.1 through FIG.5 where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments and

these embodiments are described in the context of the following exemplary system and/or method.
[017] FIG.1 is a functional block diagram of a system 100 for optimization framework for electricity power procurement portfolio in presence of forecast errors in accordance with some embodiments of the present disclosure.
[018] In an embodiment, the system 100 includes a processor(s) 104, communication interface device(s), alternatively referred as input/output (I/O) interface(s) 106, and one or more data storage devices or a memory 102 operatively coupled to the processor(s) 104. The system 100 with one or more hardware processors is configured to execute functions of one or more functional blocks of the system 100.
[019] Referring to the components of system 100, in an embodiment, the processor(s) 104, can be one or more hardware processors 104. In an embodiment, the one or more hardware processors 104 can be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the one or more hardware processors 104 is configured to fetch and execute computer-readable instructions stored in the memory 102. In an embodiment, the system 100 can be implemented in a variety of computing systems including laptop computers, notebooks, hand-held devices such as mobile phones, workstations, mainframe computers, servers, a network cloud and the like.
[020] The I/O interface(s) 106 can include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, a touch user interface (TUI) and the like and can facilitate multiple communications within a wide variety of networks N/W and protocol types, including wired networks, for example, LAN, cable, etc., and wireless networks, such as WLAN, cellular, or satellite. In an embodiment, the I/O interface (s) 106 can include one or more ports for connecting a number of devices (nodes) of the system 100 to one another or to another server.

[021] The memory 102 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes.
[022] Further, the memory 102 may include a database 108. Thus, the memory 102 may comprise information pertaining to input(s)/output(s) of each step performed by the processor(s) 104 of the system 100 and methods of the present disclosure. In an embodiment, the database 108 may be external (not shown) to the system 100 and coupled to the system via the I/O interface 106. Functions of the components of system 100 are explained in conjunction with functional overview of the system 100 in FIG.2 and flow diagram of FIGS.3A and 3B for document embedding to obtain average embeddings for documents.
[023] The system 100 supports various connectivity options such as BLUETOOTH®, USB, ZigBeeTM and other cellular services. The network environment enables connection of various components of the system 100 using any communication link including Internet, WAN, MAN, and so on. In an exemplary embodiment, the system 100 is implemented to operate as a stand-alone device. In another embodiment, the system 100 may be implemented to work as a loosely coupled device to a smart computing environment. The components and functionalities of the system 100 are described further in detail.
[024] FIG.2 is a functional block diagram of the system of FIG.1, in accordance with some embodiments of the present disclosure. As depicted in the architecture, the FIG.2 illustrates the functions of the components of the system 100 that includes an optimization framework for electricity power procurement portfolio in presence of forecast errors.
[025] The system 100 for optimization framework for electricity power procurement portfolio in presence of forecast errors is configured for receiving a plurality of input parameters associated with electricity power procurement in power domain, via a one or more hardware processors. The system 100 further comprises a forecasting module 202 configured for forecasting, through a time-

series forecast modelling technique to obtain a demand forecast and a market price forecast based on the plurality of historic data. According to an embodiment of the disclosure, the system 100 further comprises an error computation module 204 configured for computing a set of forecast errors, through an error computation technique using the plurality of historic data, the demand forecast and the market price forecast. The system 100 further comprises a risk model 206 configured for generating a risk model, based on the set of forecast error and the plurality of historic data to obtain a risk estimate from the risk model through a variance-covariance technique. The system 100 further comprises an optimization module 208 configured for generating a set of primary electricity power procurement parameters and further optimizing the set of primary electricity power procurement parameters, by the one or more hardware processors. The system 100 further comprises a refinement module 210 configured for optimizing refining the set of primary electricity power procurement parameters, by the one or more hardware processors, to obtain a final electricity power procurement parameter through a refining technique using the demand forecast and the plurality of historic data. The final electricity power procurement parameter is shared on the I/O interface 106, wherein final electricity power procurement parameter is representative of electricity procurement cost for a consumer to procure electricity power.
[026] The various modules of the system 100 for optimization framework for electricity power procurement portfolio in presence of forecast errors are implemented as at least one of a logically self-contained part of a software program, a self-contained hardware component, and/or, a self-contained hardware component with a logically self-contained part of a software program embedded into each of the hardware component that when executed perform the above method described herein.
[027] Functions of the components of the system 100 are explained in conjunction with functional modules of the system 100 stored in the memory 102 and further explained in conjunction with flow diagram of FIGS. 3A and 3B. The FIG.3A and FIG.3B, with reference to FIG.1, is an exemplary flow diagram

illustrating a method 300 for using the system 100 of FIG.1 according to an embodiment of the present disclosure.
[028] The steps of the method of the present disclosure will now be explained with reference to the components of the hierarchical network based diverse trajectory proposal system (100) and the modules (202-210) as depicted in FIGS.2 and the flow diagrams as depicted in FIG.3A and FIG.3B. Although process steps, method steps, techniques or the like may be described in a sequential order, such processes, methods and techniques may be configured to work in alternate orders. In other words, any sequence or order of steps that may be described does not necessarily indicate a requirement that the steps to be performed in that order. The steps of processes described herein may be performed in any order practical. Further, some steps may be performed simultaneously.
[029] At step 302 of the method (300), the one or more hardware processors are configured for receiving a plurality of input parameters associated with electricity power procurement in power domain. The input parameters comprises of a plurality of historic data and a plurality of constraints, wherein the plurality of historic data comprises of a historical market price and a historical consumer demand, and the plurality of constraints comprises a captive generation information and a risk aversion coefficient.
[030] In an embodiment, the historical market price and the historical demand relates to the time series data. An example of the time-series data that represents historical market price and the historical demand is illustrated in the FIG.4, wherein the x-axis represents time and the y-axis represents market price. Further the captive generation information includes details such as captive generation cost, time of the day and a risk aversion coefficient represents risk appetite of a consumer, i.e., a factor by how much a consumer is willing to take risk and risk aversion coefficient are usually set between 1 (low risk averse) to 5 (high risk averse).
[031] At step 304 of the method (300), the one or more hardware processors 104 forecast via the forecasting module 202 a demand forecast and a

market price forecast through a time-series forecast modelling technique based on the plurality of historic data.
[032] In an embodiment, the time-series forecast modelling technique includes one of an integrated auto-regressive moving average (ARIMA) and an artificial neural network. The set of forecast errors comprises of a demand forecast error and a market price forecast error. In ARIMA based time series forecasting model, the plurality of historic data which is in time series format, regress over the past values of the variable and past forecast errors. Optimal number of auto-regression and moving average terms is estimated using known techniques such as Akaike Information Criterion (AIC) or Bayesian Information Criterion (BIC). Further an ARIMA model is estimated using maximum likelihood criteria results in fitted values of auto-regression and moving average coefficients. These coefficients are used to predict the future values of the random variable that includes the demand forecast and the market price forecast. Further independent ARIMA models have been generated for each time block of a day.
[033] At step 306 of the method (300), the one or more hardware processors 104 compute via the error computation module a set of forecast errors through an error computation technique using the plurality of historic data, the demand forecast and the market price forecast.
[034] In an embodiment, the set of forecast errors comprises of a demand forecast error and a market price forecast error. The set of forecast errors are computed based on the error computation technique wherein the demand forecast error is computed based on a comparison between demand forecast and the historic demand while the market price forecast error is computed based on the error computation technique by a comparison between the market price forecast and the historic market price. In an embodiment, associated with market price (Q(t)), demand forecast error (qd(t)) & market price forecast error (qd(t)). The elements of Q(t) are represented by variance of the market price σm2(t), the value of σm2(t) is determined using the historical market price logs for the previous one year. Elements of qp(t) & qd(t) are represented by variance of the market price

forecasting error σe2p(t) & the demand forecasting error σe2p(t) where σe2p(t) is estimated by testing the performance of the demand forecasting model on the previous month’s data. Similarly, σe2p(t) is estimated by testing the market price forecasting model in the previous one year.
[035] The computation of set of forecast errors can be expressed as shown below :
epi(t)) = ĉsi(t) - csi(t) (1)
where,
epi(t) is the market price forecast error
ĉsi(t) is the market price forecast
csi(t) is the historic market price
(edi(t)) = (d̂ (t)) - (d(t)) (2)
where,
(edi(t) is the demand forecast error d̂ (t) is the demand forecast d(t) is the historic demand price [036] At step 308 of the method (300), the one or more hardware processors 104 generate via the risk model 206, a risk model based on the set of forecast error and the plurality of historic data, to obtain a risk estimate from the risk model through a variance-covariance technique. The risk estimate comprises of a demand forecast error risk estimate, a market price forecast error risk estimate, and a historic market price risk estimate.
[037] In an embodiment, the variance/risk in the price forecast error is weighted by the compliment of the correlation between a variance of market price forecast error and a variance of market price volatility, wherein higher the correlation, lower the weight . During generation of the risk model, the effects of market price forecast error is considered only when its risk is uncorrelated with the market price forecast to avoid double penalization.
[038] In an embodiment, the demand forecast error risk estimate is estimated from the risk model through a variance-covariance technique using the

demand forecast error, wherein the demand forecast error is represented in its vector form referred to as demand forecast error vector. The estimation of demand forecast error risk estimate is expressed as shown below :
Demand forecast error risk estimate (Variance of demand forecast error),
(3) where,
ed is a demand forecast error vector, edj(t) is a jth demand forecast error, e ̅d̅(t) is a mean of the demand forecast error vector and N is a length of the demand forecast error vector. [039] In an embodiment, the market price forecast error risk estimate is estimated from the risk model through a variance-covariance technique using the market price forecast error, wherein the market price forecast error is represented in its vector form referred to as market price forecast error vector. The estimation of market price forecast error risk estimate is expressed as shown below :
Market price forecast error risk estimate (Variance of market price forecast
(4) where,
ep is a market price forecast error vector, epj(t) is a jth market price forecast error, e̅ ̅p̅(t) is a mean of the market price forecast error vector and N is a length of the market price forecast error vector. [040] In an embodiment, the historic market price risk estimate is estimated from the risk model through a variance-covariance technique using the historic market price, wherein the historic market price forecast error is represented in its vector form referred to as a historic market price forecast error vector. The estimation of historic market price forecast error risk estimate is expressed as shown below :
Historic market price risk estimate

where,
m is a historic market price vector, csj(t) is a the jth historic market price, cs(t) is a mean of the historic market price vector and N is a length of the historic market prices vector. [041] At step 310 of the method (300), the one or more hardware processors 104 generate via the optimization module 208 a set of primary electricity power procurement parameters and optimizing the set of primary electricity power procurement parameters through a procure-optimization technique based on the plurality of constraints, the demand forecast, the market price forecast and the risk estimate.
[042] The set of primary electricity power procurement parameter represents an electricity procurement cost for a consumer and comprises of a captive generation allocation parameter, a procurement cost parameter and a market allocation parameter. The procure-optimization technique is expressed as:

where,
cT(t) is a transpose of matrix of the price of a “n" sources available at a time ‘t’,
x(t) is one or more allocations across the n sources at the time ‘t’.
k is the per-defined risk aversion coefficient (set between 1 (low risk averse) to 5 (high risk averse)),