This paper presents a direct model reference adaptive internal model controller (DMRAIMC) for a doubly fed induction generator used in wind farms for voltage sag ride-through. The dynamic response of the machine under fault causes voltage sag which affects the behaviour of the machine. This phenomenon is simulated using MATLAB/SIMULINK and presented. Here, the DMRAIMC is developed and it is tuned using fuzzy rules, and fuzzy rules adjustment mechanism is used in this controller to exchange the reactive power during voltage sag. The d-and q-axis rotor currents are controlled directly with DMRAIMC to improve the reactive power exchange of the system. The performance is compared with the conventional DMRAIMC with MIT rule adjustment mechanism. The flexibility of the proposed method in shunt connection with grid is illustrated.
NomenclatureV s stator voltage (V) R s stator resistance ( ) i s stator current (A) λ s stator flux (wb turns) V r rotor voltage (V) R r rotor resistance ( ) i r rotor current (A) λ r rotor flux (wb turns) 230 N. Amuthan et al. V ds stator direct-axis voltage (V) i ds stator direct-axis current (A) λ ds stator direct-axis flux (wb turns) V qs stator quadrature-axis voltage (V) i qs stator quadrature-axis current (A) λqs stator quadrature-axis flux (wb turns) V dr rotor direct-axis voltage (V) i dr rotor direct-axis current (A) λ dr rotor direct-axis flux (wb turns) V qr rotor quadrature-axis voltage (V) i qr rotor quadrature-axis current (A) λ qr rotor quadrature-axis flux (wb turns) L r leakage inductance (H) L m magnetizing inductance (H) L sl stator leakage inductance (H) L rl rotor leakage inductance (H) W o base speed (rad/s) W k speed of the reference frame (rad/s) W m rotor speed (rad/s) C capacitance (F) J inertia of the rotor (kg m 2 ) D active damping torque P d/dt (derivative function)
Distributed deep learning is a type of machine learning that uses neural networks to learn and make predictions at scale. This is achieved by having many different computer systems that are connected via the internet. This allows for more parallel processing and faster results. In addition, when it comes to IoT, this type of technology can be used in conjunction with sensors and other devices to create more accurate predictions about the environment around us. Distributed deep learning can be used in many ways with the IoT because it can be applied to various aspects of IoT data processing, such as image recognition, speech recognition, natural language processing (NLP), or anomaly detection. The neural net is the most computationally intensive component of the system, and it requires a significant amount of energy. To make this system more cost-effective, there are two ways to lower the number of memory accesses: by reducing the size of images (so precision decreases), or by increasing network bandwidth so that there are fewer loop iterations required for each memory access.
Deep learning is a new approach to artificial intelligence that enables edge-computing systems to learn from data and take decisions without human intervention. Edge computing is a technique for coping with the increasing demand for streaming data. This is especially important in the case of applications that involve computationally intensive tasks such as driverless cars, autonomous drones, and smart cities. Edge computing is the provision of computing, big data analytics, and storage in such a way that the data comes to the processing power and not vice versa. It relies on a decentralized approach where computational resources are provided at the edge of networks. Edge computing is an emerging field that's getting attention from many vendors and researchers. The data generated by IoT devices is usually too large and complex for cloud-based storage and processing. That's why edge computing can handle data at the source of generation in real time, which speeds up the process of decision making.
There is software that can be installed on a computer to control how an autonomous controller operates in a vehicle. The central processing unit (CPU) of the controller receives input from position sensors, processes that input, and then outputs operation control signals that indicate the updated course that the vehicle will take. A programming interface and operation controls are also included as parts of the controller. This interface helps to facilitate communication between the various controller components. Inputs from position sensors are normalized for the processor by the controller, which then sends outputs from itself as inputs into the operation control mechanisms. It is a stand-alone device that can be configured to function with a broad range of distant sensors and control mechanisms. As a direct consequence of the rapid spread of new technologies, edge computing has developed into a more widespread practice. Users may be able to have a more individualized and interactive experience in their day-to-day lives thanks to edge computing and edge devices.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.