Claims:WE CLAIM: 1. A processor implemented method (200), the method comprising: receiving (202), by one or more hardware processors, a global state corresponding to a plurality of wind turbines and a current global reward from a centralized Command Center (CC) integrated with the plurality of wind turbines; computing (204), by the one or more hardware processors, a global state vector based on the global state corresponding to each of the plurality of wind turbines by a pre-trained auto-encoder; simultaneously segmenting (206), by the one or more hardware processors, the global state into a plurality of local states, wherein a number of states in the plurality of local states is equal to a number of turbines; obtaining (208), by the one or more hardware processors, an optimum joint action vector comprising a blade pitch angle and a turbine yaw angle for each of the plurality of wind turbines from a dynamic joint action space based on the global state vector, the plurality of local states and the current global reward, wherein the dynamic joint action space is generated based on a pitch action space and a yaw action space, wherein the pitch action space is generated by a pre-trained pitch Deep Q Network (DQN), and wherein the yaw action space is generated by a pre-trained yaw DQN; and actuating (210), by the one or more hardware processors, each of the plurality of wind turbines based on a corresponding optimum joint action vector. 2. The method as claimed in claim 1, wherein the global state comprises an angular velocity and a resultant wind speed corresponding to each of the plurality of wind turbines. 3. The method as claimed in claim 1, wherein the global state is generated based on sensor data obtained from a plurality of sensors corresponding to each of the plurality of wind turbines. 4. The method as claimed in claim 1, wherein the sensor data comprises a free-stream wind speed, a direction, a resultant wind speed, a rotor angular velocity and a generated power corresponding to each of the plurality of wind turbines. 5. The method as claimed in claim 1, wherein the blade pitch angle and the turbine yaw angle corresponding to each of the plurality of wind turbines with a maximum current global reward is selected as the optimum joint action vector. 6. The method as claimed in claim 1, wherein the current global reward is computed based on a farm level total power, a pre-determined maximum power and a normalized damage to the turbine blades. 7. The method as claimed in claim 1, wherein the pre-trained pitch DQN is trained by: initializing a pitch action space corresponding to the pitch DQN with a corresponding first predefined random values, wherein the first predefined random values are selected within predefined bounds; initializing a pitch Q vector based on the initialized pitch action space, wherein the pitch Q vector comprises a plurality of pitch local states, the global state vector, a blade pitch angle corresponding to each of the plurality of pitch local states and a corresponding expected discounted cumulative reward, wherein each of the plurality of pitch local states comprises a rotor angular velocity and a resultant wind speed; updating the pitch Q vector by learning a plurality of pitch local states, the global state vector and corresponding blade pitch angles by a Q-learning approach; and updating the pitch action space based on the updated pitch Q vector by an epsilon-greedy approach. 8. The method as claimed in claim 1, wherein the pre-trained yaw DQN is trained by: initializing a yaw action space corresponding to the yaw DQN with a corresponding second predefined random values, wherein the second predefined random values are selected within predefined bounds; initializing a yaw Q vector based on the initialized yaw action space, wherein the yaw Q vector comprises a plurality of yaw local states, the global state vector, a turbine yaw angle corresponding to each of the plurality of yaw local states and a corresponding expected discounted cumulative reward, wherein each of the plurality of yaw local states comprises a rotor angular velocity and a resultant wind speed; updating the yaw Q vector by learning a plurality of yaw local states, the global state vector and corresponding turbine yaw angles by a Q-learning approach; and updating the yaw action space based on the updated yaw Q vector by the epsilon-greedy approach. 9. A system (100) comprising: at least one memory (104) storing programmed instructions; one or more Input /Output (I/O) interfaces (112); and one or more hardware processors (102) operatively coupled to the at least one memory (104), wherein the one or more hardware processors (102) are configured by the programmed instructions to: receive a global state corresponding to a plurality of wind turbines and a current global reward from a centralized Command Center (CC) integrated with the plurality of wind turbines; compute a global state vector based on the global state corresponding to each of the plurality of wind turbines by a pre-trained auto-encoder; obtain an optimum joint action vector comprising a blade pitch angle and a turbine yaw angle for each of the plurality of wind turbines from a dynamic joint action space based on the global state vector, the global state and the current global reward, wherein the dynamic joint action space is generated based on a pitch action space and a yaw action space, wherein the pitch action space is generated by a pre-trained pitch Deep Q Network (DQN), and wherein the yaw action space is generated by a pre-trained yaw DQN; and actuate each of the plurality of wind turbines based on a corresponding optimum joint action vector. 10. The system of claim 9, wherein the global state comprises an angular velocity and a resultant wind speed corresponding to each of the plurality of wind turbines. 11. The system of claim 9, wherein the global state is generated based on sensor data obtained from a plurality of sensors corresponding to each of the plurality of wind turbines. 12. The system of claim 9, wherein the sensor data comprises a free-stream wind speed, a direction, a resultant wind speed, a rotor angular velocity and a generated power corresponding to each of the plurality of wind turbines. 13. The system of claim 9, wherein the blade pitch angle and the turbine yaw angle corresponding to each of the plurality of wind turbines with a maximum current global reward is selected as the optimum joint action vector. 14. The system of claim 9, wherein the current global reward is computed based on a farm level total power, a pre-determined maximum power and a normalized damage to the turbine blades. 15. The system of claim 9 claim 1, wherein the pre-trained pitch DQN is trained by: initializing a pitch action space corresponding to the pitch DQN with a corresponding first predefined random values, wherein the first predefined random values are selected within predefined bounds; initializing a pitch Q vector based on the initialized pitch action space, wherein the pitch Q vector comprises a plurality of pitch local states, the global state vector, a blade pitch angle corresponding to each of the plurality of pitch local states and a corresponding expected discounted cumulative reward, wherein each of the plurality of pitch local states comprises a rotor angular velocity and a resultant wind speed; updating the pitch Q vector by learning a plurality of pitch local states, the global state vector and corresponding blade pitch angles by a Q-learning approach; and updating the pitch action space based on the updated pitch Q vector by an epsilon-greedy approach. 16. The system of claim 9, wherein the pre-trained yaw DQN is trained by: initializing a yaw action space corresponding to the yaw DQN with a corresponding second predefined random values, wherein the second predefined random values are selected within predefined bounds; initializing a yaw Q vector based on the initialized yaw action space, wherein the yaw Q vector comprises a plurality of yaw local states, the global state vector, a turbine yaw angle corresponding to each of the plurality of yaw local states and a corresponding expected discounted cumulative reward, wherein each of the plurality of yaw local states comprises a rotor angular velocity and a resultant wind speed; updating the yaw Q vector by learning a plurality of yaw local states, the global state vector and corresponding turbine yaw angles by a Q-learning approach; and updating the yaw action space based on the updated yaw Q vector by the epsilon-greedy approach. Dated this 28th Day of June 2021 (Adheesh Nargolkar) of Khaitan & Co Reg No IN-PA-1086 , Description:TECHNICAL FIELD The disclosure herein generally relates to the field of renewable energy and, more particular, to a method and system for scalable wind farm control using artificial intelligence. BACKGROUND Wind energy is a fast-growing source of renewable energy. While sustainability is gaining traction as a driver for wind power, the economics of generation still matter in competing with conventional power sources. Therefore, there is a need for intelligently maximizing the power yield from wind turbines. On the flip side, higher power production in a turbine can cause higher mechanical stress and higher fatigue due to the rapidity of changes in stress levels. This is especially the case with larger-sized turbines with more flexible components. However, increasing fatigue results in decreasing lifetime of a turbine. Hence, optimization of the power production over the lifetime of a turbine should aim to minimize the fatigue endured. In conventional methods, turbines are controlled individually, and each turbine tries to maximize its power production through a proportional-integral-derivative (PID) controller. Often, a plurality of wind turbines are owned by a single owner which needs a centralized control to optimize the yield and the health of turbines at a farm-level rather than at an individual level. However, joint control needs to process a plurality of data from the plurality of wind turbines together which creates scalability problem. Hence it is challenging to provide a centralized farm level control of the wind turbines by addressing scalability issues. SUMMARY 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 scalable wind farm control using artificial intelligence is provided. The method includes receiving, by one or more hardware processors, a global state corresponding to a plurality of wind turbines and a current global reward from a centralized Command Center (CC) integrated with the plurality of wind turbines. Further, the method includes computing by the one or more hardware processors, a global state vector based on the global state corresponding to each of the plurality of wind turbines by a pre-trained auto-encoder. Furthermore, the method includes simultaneously segmenting by the one or more hardware processors, the global state into a plurality of local states, wherein a number of states in the plurality of local states is equal to a number of turbines. Furthermore, the method includes obtaining by the one or more hardware processors, an optimum joint action vector comprising a blade pitch angle and a turbine yaw angle for each of the plurality of wind turbines from a dynamic joint action space based on the global state vector, the plurality of local states, and the current global reward, wherein the dynamic joint action space is generated based on a pitch action space and a yaw action space, wherein the pitch action space is generated by a pre-trained pitch Deep Q Network (DQN), and wherein the yaw action space is generated by a pre-trained yaw DQN. Finally, the method includes actuating by the one or more hardware processors, each of the plurality of wind turbines based on a corresponding optimum joint action vector. In another aspect, a system for scalable wind farm control using artificial intelligence is provided. The system includes at least one memory storing programmed instructions, one or more Input /Output (I/O) interfaces, and one or more hardware processors operatively coupled to the at least one memory, wherein the one or more hardware processors are configured by the programmed instructions to receive a global state corresponding to a plurality of wind turbines and a current global reward from a centralized Command Center (CC) integrated with the plurality of wind turbines. Further, the one or more hardware processors are configured by the programmed instructions to compute a global state vector based on the global state corresponding to each of the plurality of wind turbines by a pre-trained auto-encoder. Furthermore, the one or more hardware processors are configured by the programmed instructions to simultaneously segment the global state into a plurality of local states, wherein a number of states in the plurality of local states is equal to a number of turbines. Further, the one or more hardware processors are configured by the programmed instructions to obtain an optimum joint action vector comprising a blade pitch angle and a turbine yaw angle for each of the plurality of wind turbines from a dynamic joint action space based on the global state vector, the plurality of local states and the current global reward, wherein the dynamic joint action space is generated based on a pitch action space and a yaw action space, wherein the pitch action space is generated by a pre-trained pitch Deep Q Network (DQN), and wherein the yaw action space is generated by a pre-trained yaw DQN. Finally, the one or more hardware processors are configured by the programmed instructions to actuate each of the plurality of wind turbines based on a corresponding optimum joint action vector. In yet another aspect, a computer program product including a non-transitory computer-readable medium having embodied therein a computer program for scalable wind farm control using artificial intelligence is provided. The computer readable program, when executed on a computing device, causes the computing device to receive a global state corresponding to a plurality of wind turbines and a current global reward from a centralized Command Center (CC) integrated with the plurality of wind turbines. Further, the computer readable program, when executed on a computing device, causes the computing device to compute a global state vector based on the global state corresponding to each of the plurality of wind turbines by a pre-trained auto-encoder. Furthermore, the computer readable program, when executed on a computing device, causes the computing device to simultaneously segment the global state into a plurality of local states, wherein a number of states in the plurality of local states is equal to a number of turbines. Furthermore, the computer readable program, when executed on a computing device, causes the computing device to obtain an optimum joint action vector comprising a blade pitch angle and a turbine yaw angle for each of the plurality of wind turbines from a dynamic joint action space based on the global state vector, the plurality of local states and the current global reward, wherein the dynamic joint action space is generated based on a pitch action space and a yaw action space, wherein the pitch action space is generated by a pre-trained pitch Deep Q Network (DQN), and wherein the yaw action space is generated by a pre-trained yaw DQN. Finally, the computer readable program, when executed on a computing device, causes the computing device to actuate each of the plurality of wind turbines based on a corresponding optimum joint action vector. 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 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: FIG. 1 is a functional block diagram of a system for scalable wind farm control using artificial intelligence, in accordance with some embodiments of the present disclosure. FIGS. 2 is an exemplary flow diagrams illustrating a processor implemented method for scalable wind farm control using artificial intelligence, implemented by the system of FIG. 1, in accordance with some embodiments of the present disclosure. FIG. 3 illustrates a relation between the optimal feature space size and the number of turbines for the processor implemented method for scalable wind farm control using artificial intelligence implemented by the system of FIG. 1, in accordance with some embodiments of the present disclosure. FIG. 4 is an exemplary architecture for the processor implemented method for scalable wind farm control using artificial intelligence implemented by the system of FIG. 1, in accordance with some embodiments of the present disclosure. FIGS. 5 to 10 are experimental results for the processor implemented method for scalable wind farm control using artificial intelligence implemented by the system of FIG. 1, in accordance with some embodiments of the present disclosure. DETAILED DESCRIPTION OF EMBODIMENTS 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 spirit and scope of the disclosed embodiments. Embodiments herein provide a method and system for scalable wind farm control using artificial intelligence for generating maximum power with minimum damage to the turbine blades of wind turbines in a wind farm. The system balances the tradeoff between increasing the power production and damage caused to the turbine blades. Initially, the system receives a global state and a global reward from a Command Center (CC) associated with the wind farm. Further, a global state vector is computed based on the global state using a pre-trained auto-encoder. Simultaneously the global state is segmented into a plurality of local states, wherein a number of states in the plurality of local states is equal to a number of turbines. An optimum joint action vector comprising a pitch angle and a yaw angle is selected based on the global state vector, the plurality of local states and the current global reward by a pitch Deep Q Network (DQN) and a yaw DQN. Each of the plurality of wind turbines are actuated using the corresponding optimum joint action vector. Referring now to the drawings, and more particularly to FIGS. 1 through 10, 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. FIG. 1 is a functional block diagram of a system 100 for scalable wind farm control using artificial intelligence, according to some embodiments of the present disclosure. The system 100 includes or is otherwise in communication with hardware processors 102, at least one memory such as a memory 104, an I/O interface 112. The hardware processors 102, memory 104, and the Input /Output (I/O) interface 112 may be coupled by a system bus such as a system bus 108 or a similar mechanism. In an embodiment, the hardware processors 102 can be one or more hardware processors. The I/O interface 112 may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like. The I/O interface 112 may include a variety of software and hardware interfaces, for example, interfaces for peripheral device(s), such as a keyboard, a mouse, an external memory, a printer and the like. Further, the I/O interface 112 may enable the system 100 to communicate with other devices, such as web servers, and external databases. The I/O interface 112 can facilitate multiple communications within a wide variety of networks and protocol types, including wired networks, for example, local area network (LAN), cable, etc., and wireless networks, such as Wireless LAN (WLAN), cellular, or satellite. For the purpose, the I/O interface 112 may include one or more ports for connecting several computing systems with one another or to another server computer. The I/O interface 112 may include one or more ports for connecting several devices to one another or to another server. The one or more hardware processors 102 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, node machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the one or more hardware processors 102 is configured to fetch and execute computer-readable instructions stored in the memory 104. The memory 104 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. In an embodiment, the memory 104 includes a plurality of modules 106. The memory 104 also includes a data repository (or repository) 110 for storing data processed, received, and generated by the plurality of modules 106. The plurality of modules 106 include programs or coded instructions that supplement applications or functions performed by the system 100 for scalable wind farm control using artificial intelligence. The plurality of modules 106, amongst other things, can include routines, programs, objects, components, and data structures, which performs particular tasks or implement particular abstract data types. The plurality of modules 106 may also be used as, signal processor(s), node machine(s), logic circuitries, and/or any other device or component that manipulates signals based on operational instructions. Further, the plurality of modules 106 can be used by hardware, by computer-readable instructions executed by the one or more hardware processors 102, or by a combination thereof. The plurality of modules 106 can include various sub-modules (not shown). The plurality of modules 106 may include computer-readable instructions that supplement applications or functions performed by the system 100 for scalable wind farm control using artificial intelligence. In an embodiment, plurality of modules 106 includes an observer module (not shown in FIG. 1), an analyzer module (not shown in FIG. 1) and a feedback module (not shown in FIG. 1). The data repository (or repository) 110 may include a plurality of abstracted piece of code for refinement and data that is processed, received, or generated as a result of the execution of the plurality of modules in the module(s) 106. Although the data repository 110 is shown internal to the system 100, it will be noted that, in alternate embodiments, the data repository 110 can also be implemented external to the system 100, where the data repository 110 may be stored within a database (not shown in FIG. 1) communicatively coupled to the system 100. The data contained within such external database may be periodically updated. For example, new data may be added into the database (not shown in FIG. 1) and/or existing data may be modified and/or non-useful data may be deleted from the database (not shown in FIG. 1). In one example, the data may be stored in an external system, such as a Lightweight Directory Access Protocol (LDAP) directory and a Relational Database Management System (RDBMS). FIGS. 2 is an exemplary flow diagram illustrating a method 200 for scalable wind farm control using artificial intelligence implemented by the system 100 of FIG. 1 according to some embodiments of the present disclosure. In an embodiment, the system 100 includes one or more data storage devices or the memory 104 operatively coupled to the one or more hardware processor(s) 102 and is configured to store instructions for execution of steps of the method 200 by the one or more hardware processors 102. The steps of the method 200 of the present disclosure will now be explained with reference to the components or blocks of the system 100 as depicted in FIG. 1 and the steps of flow diagram as depicted in FIG. 2. The method 200 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, functions, etc., that perform particular functions or implement particular abstract data types. The method 200 may also be practiced in a distributed computing environment where functions are performed by remote processing devices that are linked through a communication network. The order in which the method 200 is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method 200, or an alternative method. Furthermore, the method 200 can be implemented in any suitable hardware, software, firmware, or combination thereof. At step 202 of the method 200, the one or more hardware processors 102 are configured by the programmed instructions to receive a global state corresponding to a plurality of wind turbines and a current global reward from a centralized Command Center (CC) integrated with the plurality of wind turbines. The global state includes an angular velocity and a resultant wind speed corresponding to each of the plurality of wind turbines. The global state is generated based on sensor data obtained from a plurality of sensors corresponding to each of the plurality of wind turbines. For example, the plurality sensors include a plurality of anemometers, a plurality of wind vanes, a plurality of tachometers, a plurality of power meters and the like. The sensor data includes a free-stream wind speed, a direction, a resultant wind speed, a rotor angular velocity and a generated power corresponding to each of the plurality of wind turbines. The current global reward is updated periodically. The current global reward is computed based on a farm level total power, a pre-determined maximum power and a normalized damage (D) to the turbine blades. The formula for calculating the current global reward is given in equation (1), where 0