A continuous energy supply to the load side is required by modern power systems. This calls for a sound understanding of how to forecast load demand in the present and the future with the least ...degree of inaccuracy. Typically, a sequential method with two steps-forecasting and optimization-is used to derive judgments from data. For achieving this goal, optimized power flow is focused in this paper through load forecasting, mode selection, and optimization of power forecasting. Firstly, load forecasting is implemented using time series, and economic and weather-related information for the different consumer's load. Then mode selection is implemented using Hidden Markov Model that determines the requested load for grid-connected or RES mode. When composite RES is developed, the percentage of serviced load rises as more renewable energy sources are added. Following the implementation of the consumer load and mode selection, optimization is used to improve the power flow. The empirical findings show enhanced prescriptive performance when compared to answers found in single- and multi-household contexts. Also, we offer insightful information on how explaining performance is described.
Nowadays, non-conventional energy sources like solar, wind, geothermal, and small hydro play a vital role in generating electricity. Among these, solar energy is utilized in urban and rural areas. ...When the sunlight falls on the solar plate, the PV cell produces charge carriers that produce an electric current. A photo voltaic cell is used when it works at the maximum power point. Traditional maximum power point tracking (MPPT) techniques are easier to structure and apply but perform worse than AI-based systems. The main objective of this paper is to develop an intelligent system to determine the maximum power point using artificial neural networks. This system uses the radial basis function network (RBFN) architecture to improve MPPT control for PV systems. The response characteristics of the photo-voltaic array are non-linear due to insolation, temperature variation, the incident light angle, and the solar cell's surface condition. Hence, this must be checked to develop the system's most significant amount of power. The MPPT controller's response can be recycled to monitor the DC-DC boost converters for maximum efficiency.
Wind power is a clear feature of intermittent, nonstationary, and difficult fluctuations, making it challenging for achieving consistent wind power generation. Assuming the restricted nature of ...typical energy resources and the developing difficulties of environmental problems, several countries are starting with developing novel energy resources which are considered for environmental and renewable safety. Amongst the several novel energy resources, wind energy was abundant, doesn't cause pollution, has minimum cost, and does not deplete. Accurate wind power predictive is enhance the reliability and safety of power grid function. Therefore, this study presents a sparrow search optimization with deep belief network for wind power prediction (SSODBN-WPP) technique. The SSODBN-WPP technique follows a two stage process namely prediction and parameter tuning. At the initial stage, the SSODBN-WPP technique employs DBN method for wind power prediction. Next, the SSO algorithm is used to adjust the core hyperparameters of the DBN algorithm. The efficacy of the SSODBN-WPP method is tested on a comprehensive set of simulations that take place on wind power dataset. A comparison study of the SSODBN-WPP technique reported its betterment over other predictive approaches.
Theft of electricity is a major problem that causes financial losses and inconsistent service for paying consumers for power distribution companies all over the world. The safety of the power grid ...depends on the ability to identify and stop electricity theft. The use of deep learning techniques has shown great promise in recent years, particularly in the areas of computer vision and natural language processing. This study recommends a random forest-based ensemble deep learning method for identifying cases of electricity theft. The proposed ensemble deep learning model leverages the best features of many kinds of deep learning architectures, including stacked Convolutional Neural Networks (CNN)and Long Short-Term Memory (LSTM). Each architecture has its own strengths when it comes to monitoring normal and abnormal electrical use for signs of theft. The final forecast is derived by adding together the predictions of the different models in the random forest ensemble. The ensemble model is trained using a massive dataset of energy usage records and theft information. Information about consumption patterns is extracted using feature engineering methods once the dataset has been preprocessed to get rid of noise and outliers. This preprocessed dataset is used to train the ensemble model, which then optimizes its parameters to reduce prediction errors. We use many measures, including accuracy, precision, recall, and F1-score, to assess the proposed ensemble deep learning model's performance. Experiments are run against both conventional machine learning methods and standalone deep learning models to prove that the ensemble method is superior. The findings demonstrate that the ensemble model is more accurate and has a greater detection rate, making it suitable for spotting energy theft.
In today's quick-paced society, renewable energy plays a significant role in producing electricity. Nature offers a variety of non-conventional energy sources. However, solar photovoltaic systems use ...solar energy more frequently. The sun energy is transformed into consistent electrical energy in solar photovoltaic systems. However, the solar photovoltaic cell's response is not consistent. For the purposes of simulation and control, a PV panel model is required. Onlywhen a PV panel is operating at its Maximum Power Point (MPP) and is being used to its full potential. This paper explores the Extremum Seeking Control (ESC) algorithm and MPPT approach for a standalone photovoltaic system. The simulations are developed and run in the MATLAB environment. When compared to the well-tuned ESC to other MPPT algorithms, it is more efficient.
Fuzzy Logic Based Maximum Power Point Tracking Design Sahu, Jayanta Kumar; Panda, Babita; Patra, Jyoti Prasad ...
2022 4th International Conference on Smart Systems and Inventive Technology (ICSSIT),
2022-Jan.-20
Conference Proceeding
Need of renewable sources is increasing multifold day by day. The most abundant renewable source that is available in the environment is solar energy. Solar energy has to be converted into electrical ...energy for daily use. This can be achieved by using photovoltaic (PV) system. But the efficiency of a PV system is very less since it is characterized by many parameters like irradiance, temperature, latitude, rainfall, humidity and mechanical load. Since the efficiency is low, it is necessary to operate on maximum power from the solar cells using maximum power point tracking (MPPT). There are numerous proposed ways for tracking the maximum power point, with the Perturb and Observe(P&O) method being the most extensively used and competitive with other MPPT methods. This paper explains about designing a standalone PV system in partial shading conditions and implementation of fuzzy logic based solar PV system. This study and observation are carried out in MATLAB Simulink model and the performance of the system is analyzed.
