1. A method of forecasting indoor temperature of a building, the method comprising: selecting, by a temperature forecasting system, a set of model coefficients, from a plurality of predetermined sets of model coefficients, based on a type of the building, wherein each coefficient in the set of model coefficients relates to indoor temperature of the building; creating, by the temperature forecasting system, a plurality of training sets using a random combination of one or more model coefficients in the selected set of model coefficients; initiating, by the temperature forecasting system, a plurality of forecasting models for forecasting indoor temperature of the building based on historical data related to the type of the building and by assigning one of the plurality of training sets to each of the plurality of forecasting models; comparing, by the temperature forecasting system, a forecasted indoor temperature value obtained from each of the plurality of forecasting models with an actual indoor temperature value of the building; and identifying, by the temperature forecasting system, a best-fit forecasting model among the plurality of forecasting models based on the comparison and forecasting the indoor temperature of the building using the best-fit forecasting model.

2. The method as claimed in claim 1, wherein the plurality of predetermined sets of model coefficients are generated based on a multi-model simulation of data relating to one or more characteristics of each type of buildings.

3. The method as claimed in claim 1, wherein each of the plurality of forecasting models are pre-trained using the historical data related to the type of the building.

4. The method as claimed in claim 1, wherein the historical data related to the type of the building comprises indoor temperature readings of the building, indoor humidity readings of the building, date and time of measurement of the indoor temperature and indoor humidity, weather data and solar irradiation data associated with the building.

5. The method as claimed in claim 1, wherein identifying the best-fit forecasting model comprises determining if the forecasted indoor temperature value obtained from each of the plurality of forecasting models is within a predefined accuracy range of the actual indoor temperature value.

6. The method as claimed in claim 5, wherein each of the plurality of forecasting models are continuously trained using corresponding training sets and a corresponding output of the comparison, until the forecasted indoor temperature value of at least one of the plurality of forecasting models reaches the predefined accuracy range.

7. The method as claimed in claim 1 further comprises segregating the coefficients in the training set of the best-fit forecasting model into static coefficients and dynamic coefficients based on predetermined segregation parameters comprising at least one of building characteristics, human actions and environmental changes associated with the building.

8. The method as claimed in claim 7, wherein the static coefficients and the dynamic coefficients are used for initiating the best-fit forecasting model in one or more subsequent zones of the building, wherein the dynamic coefficients are modified according to real-time values of the predetermined segregation parameters associated with the one or more subsequent zones.

9. A temperature forecasting system for forecasting indoor temperature of a building, the temperature forecasting system comprising: a processor; and a memory, communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which on execution, cause the process to: select a set of model coefficients from a plurality of predetermined sets of model coefficients based on a type of the building, wherein each coefficient in the set of model coefficients relates to indoor temperature of the building; create a plurality of training sets using a random combination of one or more model coefficients in the selected set of model coefficients; initiate a plurality of forecasting models for forecasting indoor temperature of the building based on historical data related to the type of the building and by assigning one of the plurality of training sets to each of the plurality of forecasting models; compare a forecasted indoor temperature value obtained from each of the plurality of forecasting models with an actual indoor temperature value of the building; and identify a best-fit forecasting model among the plurality of forecasting models based on the comparison and forecasting the indoor temperature of the building using the best-fit forecasting model.

10. The temperature forecasting system as claimed in claim 9, wherein the processor generates the plurality of predetermined sets of model coefficients based on a multi-model simulation of data relating to one or more characteristics of each type of buildings.

11. The temperature forecasting system as claimed in claim 9, wherein each of the plurality of forecasting models are pre-trained using the historical data related to the type of the building.

12. The temperature forecasting system as claimed in claim 9, wherein the historical data related to the type of the building comprises indoor temperature readings of the building, indoor humidity readings of the building, date and time of measurement of the indoor temperature and indoor humidity, weather data and solar irradiation data associated with the building.

13. The temperature forecasting system as claimed in claim 9, wherein the processor identifies the best-fit forecasting model by determining if the forecasted indoor temperature value obtained from each of the plurality of forecasting models is within a predefined accuracy range of the actual indoor temperature value.

14. The temperature forecasting system as claimed in claim 13, wherein the processor continuously trains each of the plurality of forecasting models using corresponding training sets and a corresponding output of the comparison, until the forecasted indoor temperature value of at least one of the plurality of forecasting models reaches the predefined accuracy range.

15. The temperature forecasting system as claimed in claim 9, wherein the processor segregates the coefficients in the training set of the best-fit forecasting model into static coefficients and dynamic coefficients based on predetermined segregation parameters comprising at least one of building characteristics, human actions and environmental changes associated with the building.

16. The temperature forecasting system as claimed in claim 15, wherein the processor uses the static coefficients and the dynamic coefficients for initiating the best-fit forecasting model in one or more subsequent zones of the building, wherein the processor modifies the dynamic coefficients according to real-time values of the predetermined segregation parameters associated with the one or more subsequent zones. Dated this 1st day of March, 2021 Sandeep N P IN/PA-2851 K & S Partners Agent for the Applicant , Description:FORM 2 THE PATENTS ACT 1970 [39 OF 1970] & THE PATENTS RULES, 2003 COMPLETE SPECIFICATION [See section 10; Rule 13] TITLE: “SYSTEM AND METHOD FOR FORECASTING INDOOR TEMPERATURE OF A BUILDING” Name and Address of the Applicant: HITACHI, LTD., 6-6, Marunouchi 1-chome, Chiyoda-ku, Tokyo 100-8280, Japan. Nationality: JAPAN The following specification particularly describes the invention and the manner in which it is to be performed. TECHNICAL FIELD The present subject matter is, in general, related to Heating Ventilation and Air Conditioning (HVAC) control systems, but not exclusively, to method and system for forecasting indoor temperature of a building. BACKGROUND Indoor temperature control refers to a process of maintaining interior of a building within a comfortable, uniform and controlled temperature range. In simple words, indoor temperature control is the mechanism of limiting how much the temperature changes within a building. Indoor temperature control becomes a key factor for achieving comfort of human occupants and optimum operation of Heating, Ventilation and Air Conditioning (HVAC) devices in the building. Also, control strategies for optimum operation and for minimizing energy consumption of the HVAC depends on the indoor temperature. Therefore, indoor temperature forecasting becomes important for designing energy saving control strategies for the HVAC devices. Existing temperature forecasting models either require detailed physical data for implementing and training physical models or lot of historical data for training and deploying data driven forecasting models. In both the cases, one might experience longer training and deployment time and higher cost. Therefore, it would be advantageous to have a temperature forecasting mechanism that takes less build time and is cost effective, without compromising on the forecasting accuracy. The information disclosed in this background of the disclosure section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art. SUMMARY Disclosed herein is a method for forecasting indoor temperature of a building. The method comprises selecting, by a temperature forecasting system, a set of model coefficients, from a plurality of predetermined sets of model coefficients, based on a type of the building. Each coefficient in the set of model coefficients relates to indoor temperature of the building. Further, the method comprises creating a plurality of training sets using a random combination of one or more model coefficients in the selected set of model coefficients. Upon creating the plurality of training sets, the method comprises initiating a plurality of forecasting models for forecasting indoor temperature of the building based on historical data related to the type of the building and by assigning one of the plurality of training sets to each of the plurality of forecasting models. Thereafter, the method comprises comparing a forecasted indoor temperature value obtained from each of the plurality of forecasting models with an actual indoor temperature value of the building. Finally, the method comprises identifying a best-fit forecasting model among the plurality of forecasting models based on the comparison and forecasting the indoor temperature of the building using the best-fit forecasting model. Further, the present disclosure relates to a temperature forecasting system for forecasting indoor temperature of a building. The temperature forecasting system comprises a processor and a memory. The memory is communicatively coupled to the processor and stores processor-executable instructions, which on execution, cause the process to select a set of model coefficients from a plurality of predetermined sets of model coefficients based on a type of the building. Each coefficient in the set of model coefficients relates to indoor temperature of the building. Further, the instructions cause the processor to create a plurality of training sets using a random combination of one or more model coefficients in the selected set of model coefficients. Thereafter, the instructions cause the processor to initiate a plurality of forecasting models for forecasting indoor temperature of the building based on historical data related to the type of the building and by assigning one of the plurality of training sets to each of the plurality of forecasting models. Furthermore, the instructions cause the processor to compare a forecasted indoor temperature value obtained from each of the plurality of forecasting models with an actual indoor temperature value of the building. Finally, the instructions cause the processor to identify a best-fit forecasting model among the plurality of forecasting models based on the comparison and forecasting the indoor temperature of the building using the best-fit forecasting model. The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description. BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWINGS The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, explain the disclosed principles. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the figures to reference like features and components. Some embodiments of system and/or methods in accordance with embodiments of the present subject matter are now described, by way of example only, and regarding the accompanying figures, in which: FIG. 1A illustrates an exemplary arrangement for forecasting indoor temperature in a building in accordance with some embodiments of the present disclosure. FIG. 1B illustrates an exemplary arrangement indicating usability of the proposed temperature forecasting system in accordance with some embodiments of the present disclosure. FIG. 2 shows a detailed block diagram of the temperature forecasting system in accordance with some embodiments of the present disclosure. FIG. 3 illustrates a method of extending temperature forecasting to multiple zones of a building in accordance with some embodiments of the present disclosure. FIG. 4 shows a flowchart illustrating a method of forecasting indoor temperature in a building in accordance with some embodiments of the present disclosure. FIG. 5 illustrates a block diagram of an exemplary computer system for implementing embodiments consistent with the present disclosure. It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially represented in computer readable medium and executed by a computer or processor, whether such computer or processor is explicitly shown. DETAILED DESCRIPTION In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and will be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the specific forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the scope of the disclosure. The terms “comprises”, “comprising”, “includes”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device, or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus proceeded by “comprises… a” does not, without more constraints, preclude the existence of other elements or additional elements in the system or method. The present disclosure relates to a method and a temperature forecasting system for forecasting indoor temperature of a building. In an embodiment, the present disclosure discloses creating a real-time and/or ‘on-the-go’ model for forecasting the indoor temperature of a building. The proposed method takes in a smaller number of historic data to train and build the forecasting model. Also, by using pre-defined weight tables and/or sets of coefficients, the proposed method aims to reduce the model build time. The pre-weight tables provide initialization weights for initializing the forecasting model and are subsequently tuned to improve the model accuracy. Additionally, the proposed disclosure suggests segregating the tuned weight table into a ‘static’ and ‘dynamic’ category, which are further used to initialize forecasting models at other sites having similar structural characteristics. In the following detailed description of the embodiments of the disclosure, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration specific embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense. FIG. 1A illustrates an exemplary environment 100 for forecasting indoor temperature in a building 101 in accordance with some embodiments of the present disclosure. In an embodiment, the environment 100 may include a building 101, a temperature forecasting system 105 and a database 109 associated with the temperature forecasting system 105. In an embodiment, the building 101 may be a physical structure such as an office, a school, a house, an apartment, a theatre or a shopping complex, whose indoor temperature needs to be forecasted. In an embodiment, the temperature forecasting system 105 may be a computing system such as, without limiting to, a desktop computer, a server, a laptop or a smartphone, which may be configured for forecasting indoor temperature of the building 101 in accordance with various embodiments recited in the present disclosure. In an embodiment, the database 109 may be a storage unit used for storing historical data 110 related to the building 101. In one implementation, the database 109 may be a part of the temperature forecasting system 105. Alternatively, the database 109 may be within the building 101 or on a remote location and accessible by the temperature forecasting system 105. In an embodiment, the indoor temperature of the building 101 may be an essential input for designing control strategies for optimizing operation and energy consumption of one or more Heating, Ventilation and Air-Conditioning (HVAC) devices in the building 101. Therefore, the effectiveness of these control strategies depends on the accuracy with which the indoor temperature of the building 101 can be forecasted. The proposed temperature forecasting system 105 forecasts the indoor temperature of the building 101 with higher accuracy, while consuming lesser training resources and taking less time for training and deployment of forecasting models 107, as elaborated in the following paragraphs of the disclosure. In an embodiment, before initiating the temperature forecasting, the temperature forecasting system 105 may identify a type of the building 101. As an example, the type of the building 101 may be school buildings, office buildings, residential buildings, public buildings and the like. In an embodiment, all possible building types may be determined and stored as a reference in the temperature forecasting system 105. Subsequently, the type of the building 101, whose indoor temperature needs to be forecasted, may be determined based on a user input received from a person associated with the building 101 or an operator of the temperature forecasting model. That is, the user input may be received by providing the reference building types and prompting the user to select one of the reference building types as the type of the building 101. In an embodiment, the buildings classification may be done on the basis of building envelop and interior conditions of the building 101. As an example, all the buildings having an envelop made of ‘glass’ may be classified into a single group, while other buildings having majority of envelop made of concrete may be classified into other groups of buildings. As an example, the each building may be classified into one of the following building types, namely, ‘office’, ‘malls’, ‘schools’, ‘residential’, and the like. In an embodiment, for each type of the building 101, the temperature forecasting model may have a corresponding, predetermined set of model coefficients 103, which may be used for initializing and training temperature forecasting models 107 for that particular type of the building 101. For example, the temperature forecasting model may have distinct set of model coefficients 103 for ‘school buildings’ and ‘office buildings’. Here, the set of model coefficients 103 may be determined and/or selected based on building characteristics, and usage and temperature control requirements of each type of the buildings. As an example, since the building envelop characteristics may be different for an ‘office’ type building in comparison to that of a ‘school’ type building, the set of model coefficients 103 selected for these two types of the buildings may be different. Therefore, the set of model coefficients 103 corresponding to the ‘office buildings’ may be different from the set of model coefficients 103 corresponding to the ‘school buildings’. In an embodiment, the predetermined set of model coefficients 103 may be identified based on pre-computed analysis of historical data 110 associated with each type of the building 101. In an embodiment, once the type of the building 101 is determined based on the user input, the temperature forecasting model may select one of the plurality of predetermined sets of model coefficients 103, corresponding to the type of the building 101, for initializing and training the forecasting models 107 for the building 101. Thereafter, the temperature forecasting system 105 may create a plurality of training sets of model coefficients 103 using a random combination of one or more model coefficients in the selected set of the model coefficients. As an example, if there are ‘N’ number of model coefficients, say C1, C2, … CN, in the selected set of model coefficients 103, then the temperature forecasting system 105 may form a plurality of training sets of model coefficients 103 by randomly picking a ‘T’ number of model coefficients from the ‘N’ number of model coefficients, such that T

Claims:WE CLAIM: 1. A method of forecasting indoor temperature of a building, the method comprising: selecting, by a temperature forecasting system, a set of model coefficients, from a plurality of predetermined sets of model coefficients, based on a type of the building, wherein each coefficient in the set of model coefficients relates to indoor temperature of the building; creating, by the temperature forecasting system, a plurality of training sets using a random combination of one or more model coefficients in the selected set of model coefficients; initiating, by the temperature forecasting system, a plurality of forecasting models for forecasting indoor temperature of the building based on historical data related to the type of the building and by assigning one of the plurality of training sets to each of the plurality of forecasting models; comparing, by the temperature forecasting system, a forecasted indoor temperature value obtained from each of the plurality of forecasting models with an actual indoor temperature value of the building; and identifying, by the temperature forecasting system, a best-fit forecasting model among the plurality of forecasting models based on the comparison and forecasting the indoor temperature of the building using the best-fit forecasting model. 2. The method as claimed in claim 1, wherein the plurality of predetermined sets of model coefficients are generated based on a multi-model simulation of data relating to one or more characteristics of each type of buildings. 3. The method as claimed in claim 1, wherein each of the plurality of forecasting models are pre-trained using the historical data related to the type of the building. 4. The method as claimed in claim 1, wherein the historical data related to the type of the building comprises indoor temperature readings of the building, indoor humidity readings of the building, date and time of measurement of the indoor temperature and indoor humidity, weather data and solar irradiation data associated with the building. 5. The method as claimed in claim 1, wherein identifying the best-fit forecasting model comprises determining if the forecasted indoor temperature value obtained from each of the plurality of forecasting models is within a predefined accuracy range of the actual indoor temperature value. 6. The method as claimed in claim 5, wherein each of the plurality of forecasting models are continuously trained using corresponding training sets and a corresponding output of the comparison, until the forecasted indoor temperature value of at least one of the plurality of forecasting models reaches the predefined accuracy range. 7. The method as claimed in claim 1 further comprises segregating the coefficients in the training set of the best-fit forecasting model into static coefficients and dynamic coefficients based on predetermined segregation parameters comprising at least one of building characteristics, human actions and environmental changes associated with the building. 8. The method as claimed in claim 7, wherein the static coefficients and the dynamic coefficients are used for initiating the best-fit forecasting model in one or more subsequent zones of the building, wherein the dynamic coefficients are modified according to real-time values of the predetermined segregation parameters associated with the one or more subsequent zones. 9. A temperature forecasting system for forecasting indoor temperature of a building, the temperature forecasting system comprising: a processor; and a memory, communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which on execution, cause the process to: select a set of model coefficients from a plurality of predetermined sets of model coefficients based on a type of the building, wherein each coefficient in the set of model coefficients relates to indoor temperature of the building; create a plurality of training sets using a random combination of one or more model coefficients in the selected set of model coefficients; initiate a plurality of forecasting models for forecasting indoor temperature of the building based on historical data related to the type of the building and by assigning one of the plurality of training sets to each of the plurality of forecasting models; compare a forecasted indoor temperature value obtained from each of the plurality of forecasting models with an actual indoor temperature value of the building; and identify a best-fit forecasting model among the plurality of forecasting models based on the comparison and forecasting the indoor temperature of the building using the best-fit forecasting model. 10. The temperature forecasting system as claimed in claim 9, wherein the processor generates the plurality of predetermined sets of model coefficients based on a multi-model simulation of data relating to one or more characteristics of each type of buildings. 11. The temperature forecasting system as claimed in claim 9, wherein each of the plurality of forecasting models are pre-trained using the historical data related to the type of the building. 12. The temperature forecasting system as claimed in claim 9, wherein the historical data related to the type of the building comprises indoor temperature readings of the building, indoor humidity readings of the building, date and time of measurement of the indoor temperature and indoor humidity, weather data and solar irradiation data associated with the building. 13. The temperature forecasting system as claimed in claim 9, wherein the processor identifies the best-fit forecasting model by determining if the forecasted indoor temperature value obtained from each of the plurality of forecasting models is within a predefined accuracy range of the actual indoor temperature value. 14. The temperature forecasting system as claimed in claim 13, wherein the processor continuously trains each of the plurality of forecasting models using corresponding training sets and a corresponding output of the comparison, until the forecasted indoor temperature value of at least one of the plurality of forecasting models reaches the predefined accuracy range. 15. The temperature forecasting system as claimed in claim 9, wherein the processor segregates the coefficients in the training set of the best-fit forecasting model into static coefficients and dynamic coefficients based on predetermined segregation parameters comprising at least one of building characteristics, human actions and environmental changes associated with the building. 16. The temperature forecasting system as claimed in claim 15, wherein the processor uses the static coefficients and the dynamic coefficients for initiating the best-fit forecasting model in one or more subsequent zones of the building, wherein the processor modifies the dynamic coefficients according to real-time values of the predetermined segregation parameters associated with the one or more subsequent zones. Dated this 1st day of March, 2021 Sandeep N P IN/PA-2851 K & S Partners Agent for the Applicant , Description:FORM 2 THE PATENTS ACT 1970 [39 OF 1970] & THE PATENTS RULES, 2003 COMPLETE SPECIFICATION [See section 10; Rule 13] TITLE: “SYSTEM AND METHOD FOR FORECASTING INDOOR TEMPERATURE OF A BUILDING” Name and Address of the Applicant: HITACHI, LTD., 6-6, Marunouchi 1-chome, Chiyoda-ku, Tokyo 100-8280, Japan. Nationality: JAPAN The following specification particularly describes the invention and the manner in which it is to be performed. TECHNICAL FIELD The present subject matter is, in general, related to Heating Ventilation and Air Conditioning (HVAC) control systems, but not exclusively, to method and system for forecasting indoor temperature of a building. BACKGROUND Indoor temperature control refers to a process of maintaining interior of a building within a comfortable, uniform and controlled temperature range. In simple words, indoor temperature control is the mechanism of limiting how much the temperature changes within a building. Indoor temperature control becomes a key factor for achieving comfort of human occupants and optimum operation of Heating, Ventilation and Air Conditioning (HVAC) devices in the building. Also, control strategies for optimum operation and for minimizing energy consumption of the HVAC depends on the indoor temperature. Therefore, indoor temperature forecasting becomes important for designing energy saving control strategies for the HVAC devices. Existing temperature forecasting models either require detailed physical data for implementing and training physical models or lot of historical data for training and deploying data driven forecasting models. In both the cases, one might experience longer training and deployment time and higher cost. Therefore, it would be advantageous to have a temperature forecasting mechanism that takes less build time and is cost effective, without compromising on the forecasting accuracy. The information disclosed in this background of the disclosure section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art. SUMMARY Disclosed herein is a method for forecasting indoor temperature of a building. The method comprises selecting, by a temperature forecasting system, a set of model coefficients, from a plurality of predetermined sets of model coefficients, based on a type of the building. Each coefficient in the set of model coefficients relates to indoor temperature of the building. Further, the method comprises creating a plurality of training sets using a random combination of one or more model coefficients in the selected set of model coefficients. Upon creating the plurality of training sets, the method comprises initiating a plurality of forecasting models for forecasting indoor temperature of the building based on historical data related to the type of the building and by assigning one of the plurality of training sets to each of the plurality of forecasting models. Thereafter, the method comprises comparing a forecasted indoor temperature value obtained from each of the plurality of forecasting models with an actual indoor temperature value of the building. Finally, the method comprises identifying a best-fit forecasting model among the plurality of forecasting models based on the comparison and forecasting the indoor temperature of the building using the best-fit forecasting model. Further, the present disclosure relates to a temperature forecasting system for forecasting indoor temperature of a building. The temperature forecasting system comprises a processor and a memory. The memory is communicatively coupled to the processor and stores processor-executable instructions, which on execution, cause the process to select a set of model coefficients from a plurality of predetermined sets of model coefficients based on a type of the building. Each coefficient in the set of model coefficients relates to indoor temperature of the building. Further, the instructions cause the processor to create a plurality of training sets using a random combination of one or more model coefficients in the selected set of model coefficients. Thereafter, the instructions cause the processor to initiate a plurality of forecasting models for forecasting indoor temperature of the building based on historical data related to the type of the building and by assigning one of the plurality of training sets to each of the plurality of forecasting models. Furthermore, the instructions cause the processor to compare a forecasted indoor temperature value obtained from each of the plurality of forecasting models with an actual indoor temperature value of the building. Finally, the instructions cause the processor to identify a best-fit forecasting model among the plurality of forecasting models based on the comparison and forecasting the indoor temperature of the building using the best-fit forecasting model. The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description. BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWINGS The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, explain the disclosed principles. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the figures to reference like features and components. Some embodiments of system and/or methods in accordance with embodiments of the present subject matter are now described, by way of example only, and regarding the accompanying figures, in which: FIG. 1A illustrates an exemplary arrangement for forecasting indoor temperature in a building in accordance with some embodiments of the present disclosure. FIG. 1B illustrates an exemplary arrangement indicating usability of the proposed temperature forecasting system in accordance with some embodiments of the present disclosure. FIG. 2 shows a detailed block diagram of the temperature forecasting system in accordance with some embodiments of the present disclosure. FIG. 3 illustrates a method of extending temperature forecasting to multiple zones of a building in accordance with some embodiments of the present disclosure. FIG. 4 shows a flowchart illustrating a method of forecasting indoor temperature in a building in accordance with some embodiments of the present disclosure. FIG. 5 illustrates a block diagram of an exemplary computer system for implementing embodiments consistent with the present disclosure. It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially represented in computer readable medium and executed by a computer or processor, whether such computer or processor is explicitly shown. DETAILED DESCRIPTION In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and will be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the specific forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the scope of the disclosure. The terms “comprises”, “comprising”, “includes”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device, or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus proceeded by “comprises… a” does not, without more constraints, preclude the existence of other elements or additional elements in the system or method. The present disclosure relates to a method and a temperature forecasting system for forecasting indoor temperature of a building. In an embodiment, the present disclosure discloses creating a real-time and/or ‘on-the-go’ model for forecasting the indoor temperature of a building. The proposed method takes in a smaller number of historic data to train and build the forecasting model. Also, by using pre-defined weight tables and/or sets of coefficients, the proposed method aims to reduce the model build time. The pre-weight tables provide initialization weights for initializing the forecasting model and are subsequently tuned to improve the model accuracy. Additionally, the proposed disclosure suggests segregating the tuned weight table into a ‘static’ and ‘dynamic’ category, which are further used to initialize forecasting models at other sites having similar structural characteristics. In the following detailed description of the embodiments of the disclosure, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration specific embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense. FIG. 1A illustrates an exemplary environment 100 for forecasting indoor temperature in a building 101 in accordance with some embodiments of the present disclosure. In an embodiment, the environment 100 may include a building 101, a temperature forecasting system 105 and a database 109 associated with the temperature forecasting system 105. In an embodiment, the building 101 may be a physical structure such as an office, a school, a house, an apartment, a theatre or a shopping complex, whose indoor temperature needs to be forecasted. In an embodiment, the temperature forecasting system 105 may be a computing system such as, without limiting to, a desktop computer, a server, a laptop or a smartphone, which may be configured for forecasting indoor temperature of the building 101 in accordance with various embodiments recited in the present disclosure. In an embodiment, the database 109 may be a storage unit used for storing historical data 110 related to the building 101. In one implementation, the database 109 may be a part of the temperature forecasting system 105. Alternatively, the database 109 may be within the building 101 or on a remote location and accessible by the temperature forecasting system 105. In an embodiment, the indoor temperature of the building 101 may be an essential input for designing control strategies for optimizing operation and energy consumption of one or more Heating, Ventilation and Air-Conditioning (HVAC) devices in the building 101. Therefore, the effectiveness of these control strategies depends on the accuracy with which the indoor temperature of the building 101 can be forecasted. The proposed temperature forecasting system 105 forecasts the indoor temperature of the building 101 with higher accuracy, while consuming lesser training resources and taking less time for training and deployment of forecasting models 107, as elaborated in the following paragraphs of the disclosure. In an embodiment, before initiating the temperature forecasting, the temperature forecasting system 105 may identify a type of the building 101. As an example, the type of the building 101 may be school buildings, office buildings, residential buildings, public buildings and the like. In an embodiment, all possible building types may be determined and stored as a reference in the temperature forecasting system 105. Subsequently, the type of the building 101, whose indoor temperature needs to be forecasted, may be determined based on a user input received from a person associated with the building 101 or an operator of the temperature forecasting model. That is, the user input may be received by providing the reference building types and prompting the user to select one of the reference building types as the type of the building 101. In an embodiment, the buildings classification may be done on the basis of building envelop and interior conditions of the building 101. As an example, all the buildings having an envelop made of ‘glass’ may be classified into a single group, while other buildings having majority of envelop made of concrete may be classified into other groups of buildings. As an example, the each building may be classified into one of the following building types, namely, ‘office’, ‘malls’, ‘schools’, ‘residential’, and the like. In an embodiment, for each type of the building 101, the temperature forecasting model may have a corresponding, predetermined set of model coefficients 103, which may be used for initializing and training temperature forecasting models 107 for that particular type of the building 101. For example, the temperature forecasting model may have distinct set of model coefficients 103 for ‘school buildings’ and ‘office buildings’. Here, the set of model coefficients 103 may be determined and/or selected based on building characteristics, and usage and temperature control requirements of each type of the buildings. As an example, since the building envelop characteristics may be different for an ‘office’ type building in comparison to that of a ‘school’ type building, the set of model coefficients 103 selected for these two types of the buildings may be different. Therefore, the set of model coefficients 103 corresponding to the ‘office buildings’ may be different from the set of model coefficients 103 corresponding to the ‘school buildings’. In an embodiment, the predetermined set of model coefficients 103 may be identified based on pre-computed analysis of historical data 110 associated with each type of the building 101. In an embodiment, once the type of the building 101 is determined based on the user input, the temperature forecasting model may select one of the plurality of predetermined sets of model coefficients 103, corresponding to the type of the building 101, for initializing and training the forecasting models 107 for the building 101. Thereafter, the temperature forecasting system 105 may create a plurality of training sets of model coefficients 103 using a random combination of one or more model coefficients in the selected set of the model coefficients. As an example, if there are ‘N’ number of model coefficients, say C1, C2, … CN, in the selected set of model coefficients 103, then the temperature forecasting system 105 may form a plurality of training sets of model coefficients 103 by randomly picking a ‘T’ number of model coefficients from the ‘N’ number of model coefficients, such that T