scholarly journals An Improved Approach to Enhance Training Performance of ANN and the Prediction of PV Power for Any Time-Span without the Presence of Real-Time Weather Data

2021 ◽  
Vol 13 (21) ◽  
pp. 11893
Author(s):  
Abdul Rauf Bhatti ◽  
Ahmed Bilal Awan ◽  
Walied Alharbi ◽  
Zainal Salam ◽  
Abdullah S. Bin Humayd ◽  
...  
Keyword(s):  
Renewable Energy ◽  
Real Time ◽  
Prediction Models ◽  
Mean Squared Error ◽  
Weather Conditions ◽  
Energy System ◽  
Weather Data ◽  
Training Performance ◽  
Proposed Model ◽  
Artificial Neural Network Ann

In this work, an improved approach to enhance the training performance of an Artificial Neural Network (ANN) for prediction of the output of renewable energy systems is proposed. Using the proposed approach, a significant reduction of the Mean Squared Error (MSE) in training performance is achieved, specifically from 4.45 × 10−7 to 3.19 × 10−10. Moreover, a simplified application of the already trained ANN is introduced through which photovoltaic (PV) output can be predicted without the availability of real-time current weather data. Moreover, unlike the existing prediction models, which ask the user to apply multiple inputs in order to forecast power, the proposed model requires only the set of dates specifying forecasting period as the input for prediction purposes. Moreover, in the presence of the historical weather data this model is able to predict PV power for different time spans rather than only for a fixed period. The prediction accuracy of the proposed model has been validated by comparing the predicted power values with the actual ones under different weather conditions. To calculate actual power, the data were obtained from the National Renewable Energy Laboratory (NREL), USA and from the Universiti Teknologi Malaysia (UTM), Malaysia. It is envisaged that the proposed model can be easily handled by a non-technical user to assess the feasibility of the photovoltaic solar energy system before its installation.

scholarly journals An IoT based Low-cost Weather Monitoring System for Smart Farming

2021 ◽  
Author(s):  
L.P.S.S.K. Dayananda ◽  
A. Narmilan ◽  
P. Pirapuraj
Keyword(s):  
Liquid Crystal ◽  
Mobile Phone ◽  
Real Time ◽  
Monitoring System ◽  
Liquid Crystal Display ◽  
Low Cost ◽  
Weather Conditions ◽  
Weather Data ◽  
The Internet ◽  
Arduino Uno

Background: Weather monitoring is an important aspect of crop cultivation for reducing economic loss while increasing productivity. Weather is the combination of current meteorological components, such as temperature, wind direction and speed, amount and kind of precipitation, sunshine hours and so on. The weather defines a time span ranging from a few hours to several days. The periodic or continuous surveillance or the analysis of the status of the atmosphere and the climate, including parameters such as temperature, moisture, wind velocity and barometric pressure, is known as weather monitoring. Because of the increased usage of the internet, weather monitoring has been upgraded to smart weather monitoring. The Internet of Things (IoT) is one of the new technology that can help with many precision farming operations. Smart weather monitoring is one of the precision agriculture technologies that use sensors to monitor correct weather. The main objective of the research is to design a smart weather monitoring and real-time alert system to overcome the issue of monitoring weather conditions in agricultural farms in order for farmers to make better decisions. Methods: Different sensors were used in this study to detect temperature and humidity, pressure, rain, light intensity, CO2 level, wind speed and direction in an agricultural farm and real time clock sensor was used to measured real time weather data. The major component of this system was an Arduino Uno microcontroller and the system ran according to a program written in the Arduino Uno software. Result: This is a low-cost smart weather monitoring system. This system’s output unit were a liquid crystal display and a GSM900A module. The weather data was displayed on a liquid crystal display and the GSM900A module was used to send the data to a mobile phone. This smart weather station was used to monitor real-time weather conditions while sending weather information to the farmer’s mobile phone, allowing him to make better decisions to increase yield.

scholarly journals Weather Prediction using Advanced Machine Learning Techniques

2021 ◽  
Vol 2089 (1) ◽  
pp. 012059
Author(s):  
G. Hemalatha ◽  
K. Srinivasa Rao ◽  
D. Arun Kumar
Keyword(s):  
Linear Relationship ◽  
Weather Prediction ◽  
Weather Condition ◽  
Weather Conditions ◽  
Machine Learning Techniques ◽  
Weather Data ◽  
Learning Techniques ◽  
Proposed Model ◽  
Non Linear ◽  
The Relationship

Abstract Prediction of weather condition is important to take efficient decisions. In general, the relationship between the input weather parameters and the output weather condition is non linear and predicting the weather conditions in non linear relationship posses challenging task. The traditional methods of weather prediction sometimes deviate in predicting the weather conditions due to non linear relationship between the input features and output condition. Motivated with this factor, we propose a neural networks based model for weather prediction. The superiority of the proposed model is tested with the weather data collected from Indian metrological Department (IMD). The performance of model is tested with various metrics..

scholarly journals Similarity-based error prediction approach for real-time inflow forecasting

2013 ◽  
Vol 45 (4-5) ◽  
pp. 589-602 ◽  
Author(s):  
Mahmood Akbari ◽  
Abbas Afshar
Keyword(s):  
Real Time ◽  
Nearest Neighbor ◽  
Prediction Models ◽  
Error Prediction ◽  
K Nearest Neighbor ◽  
Forecasting Models ◽  
Main Challenge ◽  
Inflow Forecasting ◽  
Artificial Neural Network Ann ◽  
Prediction Approach

Regardless of extensive researches on hydrologic forecasting models, the issue of updating the outputs from forecasting models has remained a main challenge. Most of the existing output updating methods are mainly based on the presence of persistence in the errors. This paper presents an alternative approach to updating the outputs from forecasting models in order to produce more accurate forecast results. The approach uses the concept of the similarity in errors for error prediction. The K nearest neighbor (KNN) algorithm is employed as a similarity-based error prediction model and improvements are made by new data, and two other forms of the KNN are developed in this study. The KNN models are applied for the error prediction of flow forecasting models in two catchments and the updated flows are compared to those of persistence-based methods such as autoregressive (AR) and artificial neural network (ANN) models. The results show that the similarity-based error prediction models can be recognized as an efficient alternative for real-time inflow forecasting, especially where the persistence in the error series of flow forecasting model is relatively low.

scholarly journals Hybrid Wind–PV Frequency Control Strategy under Variable Weather Conditions in Isolated Power Systems

2020 ◽  
Vol 12 (18) ◽  
pp. 7750 ◽  
Author(s):  
Ana Fernández-Guillamón ◽  
Guillermo Martínez-Lucas ◽  
Ángel Molina-García ◽  
Jose-Ignacio Sarasua
Keyword(s):  
Renewable Energy ◽  
Power Systems ◽  
Control Strategy ◽  
Rotational Speed ◽  
Power Plants ◽  
Mean Squared Error ◽  
Frequency Control ◽  
Weather Conditions ◽  
Squared Error ◽  
Variable Weather

Over the last two decades, variable renewable energy technologies (i.e., variable-speed wind turbines (VSWTs) and photovoltaic (PV) power plants) have gradually replaced conventional generation units. However, these renewable generators are connected to the grid through power converters decoupled from the grid and do not provide any rotational inertia, subsequently decreasing the overall power system’s inertia. Moreover, the variable and stochastic nature of wind speed and solar irradiation may lead to large frequency deviations, especially in isolated power systems. This paper proposes a hybrid wind–PV frequency control strategy for isolated power systems with high renewable energy source integration under variable weather conditions. A new PV controller monitoring the VSWTs’ rotational speed deviation is presented in order to modify the PV-generated power accordingly and improve the rotational speed deviations of VSWTs. The power systems modeled include thermal, hydro-power, VSWT, and PV power plants, with generation mixes in line with future European scenarios. The hybrid wind–PV strategy is compared to three other frequency strategies already presented in the specific literature, and gets better results in terms of frequency deviation (reducing the mean squared error between 20% and 95%). Additionally, the rotational speed deviation of VSWTs is also reduced with the proposed approach, providing the same mean squared error as the case in which VSWTs do not participate in frequency control. However, this hybrid strategy requires up to a 30% reduction in the PV-generated energy. Extensive detailing of results and discussion can be also found in the paper.

Continuous Monitoring, Modeling, and Evaluation of Actual Building Energy Systems

2014 ◽  
Author(s):  
Maxim L. Sankey ◽  
Sheldon M. Jeter ◽  
Trevor D. Wolf ◽  
Donald P. Alexander ◽  
Gregory M. Spiro ◽  
...  
Keyword(s):  
Energy Consumption ◽  
Real Time ◽  
Continuous Monitoring ◽  
Energy System ◽  
Building Energy ◽  
Energy Performance ◽  
Weather Data ◽  
Practical Procedure ◽  
Heating And Cooling ◽  
Institute Of Technology

Residential and commercial buildings account for more than 40% of U.S. energy consumption, most of which is related to heating, ventilation and air conditioning (HVAC). Consequently, energy conservation is important to building owners and to the economy generally. In this paper we describe a process under development to continuously evaluate a building’s heating and cooling energy performance in near real-time with a procedure we call Continuous Monitoring, Modeling, and Evaluation (CMME). The concept of CMME is to model the expected operation of a building energy system with actual weather and internal load data and then compare modeled energy consumption with actual energy consumption. For this paper we modeled two buildings on the Georgia Institute of Technology campus. After creating our building models, internal lighting loads and equipment plug-loads were collected through electrical sub-metering, while the building occupancy load was recorded using doorway mounted people counters. We also collected on site weather and solar radiation data. All internal loads were input into the models and simulated with the actual weather data. We evaluated the building’s overall performance by comparing the modeled heating and cooling energy consumption with the building’s actual heating and cooling energy consumption. Our results demonstrated generally acceptable energy performance for both buildings; nevertheless, certain specific energy inefficiencies were discovered and corrective actions are being taken. This experience shows that CMME is a practical procedure for improving the performance of actual well performing buildings. With improved techniques, we believe the CMME procedure could be fully automated and notify building owners in real-time of sub-optimal building performance.

scholarly journals Electric Energy Consumption Prediction by Deep Learning with State Explainable Autoencoder

Energies ◽  
2019 ◽  
Vol 12 (4) ◽  
pp. 739 ◽  
Author(s):  
Jin-Young Kim ◽  
Sung-Bae Cho
Keyword(s):  
Deep Learning ◽  
Energy Demand ◽  
Prediction Models ◽  
Mean Squared Error ◽  
Electric Energy ◽  
Representation Learning ◽  
The State ◽  
Efficient System ◽  
Energy Prediction ◽  
Proposed Model

As energy demand grows globally, the energy management system (EMS) is becoming increasingly important. Energy prediction is an essential component in the first step to create a management plan in EMS. Conventional energy prediction models focus on prediction performance, but in order to build an efficient system, it is necessary to predict energy demand according to various conditions. In this paper, we propose a method to predict energy demand in various situations using a deep learning model based on an autoencoder. This model consists of a projector that defines an appropriate state for a given situation and a predictor that forecasts energy demand from the defined state. The proposed model produces consumption predictions for 15, 30, 45, and 60 minutes with 60-minute demand to date. In the experiments with household electric power consumption data for five years, this model not only has a better performance with a mean squared error of 0.384 than the conventional models, but also improves the capacity to explain the results of prediction by visualizing the state with t-SNE algorithm. Despite unsupervised representation learning, we confirm that the proposed model defines the state well and predicts the energy demand accordingly.

Comprehensive Thermodynamic Analysis of Steam Storage in a Steam Cycle in a Different Regime of Work: A Zero-Dimensional and Three-Dimensional Approach

2021 ◽  
Vol 144 (5) ◽  
Author(s):  
Paweł Ziółkowski ◽  
Natalia Szewczuk-Krypa ◽  
Anna Butterweck ◽  
Michał Stajnke ◽  
Stanisław Głuch ◽  
...  
Keyword(s):  
Renewable Energy ◽  
Energy Storage ◽  
Carbon Dioxide Emissions ◽  
Renewable Energy Sources ◽  
Three Dimensional ◽  
Weather Conditions ◽  
Energy System ◽  
Temperature Fields ◽  
Energy Sources ◽  
Accurate Analysis

Abstract Due to the current trends aiming to reduce carbon dioxide emissions by increasing the use of renewable energy sources, changes are required in the operation of coal-fired steam units. The unstable nature of renewable energy sources, depending on weather conditions, means that the amount of energy produced varies and is not always in line with peak demand. To ensure the security and stability of energy supplies in the energy system, renewable sources should cooperate with units independent of environmental conditions. With conventional steam systems, the main issue of such energy storage applied to steam turbine units is presented in this article, which, in the event of a need for a sudden reduction of the system load, prevents overloading of the boiler and turbines, improving the safety of the system. This article presents a thermodynamic model of this energy storage. A zero-dimensional (0D) model was implemented, including the operating parameters of the unit. This model directly relates to the thermodynamic parameters defined at specific points of the thermodynamic cycle. Based on the 0D model, it was shown that the process of loading the energy storage with steam leads to a load reduction of up to 4%. Conversely, when discharging the stored energy, the net power of the steam block may increase by 0.4%. For more detailed analysis, a three-dimensional (3D) nonequilibrium with including cross effects approach was applied. This approach is based on flow models, with phase transitions that determine temperature fields, densities, and phase transition in relevant space, and is used for more accurate analysis. Here, we investigate the relationship between the 0D and 3D approaches in the context of steam storage. The combination of these two approaches is the fundamental novelty of this article.

scholarly journals Towards an End-to-End Framework of CCTV-Based Urban Traffic Volume Detection and Prediction

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 629
Author(s):  
Maria V. Peppa ◽  
Tom Komar ◽  
Wen Xiao ◽  
Phil James ◽  
Craig Robson ◽  
...  
Keyword(s):  
Real Time ◽  
Prediction Models ◽  
Weather Conditions ◽  
Traffic Volume ◽  
Urban Traffic ◽  
Transport Systems ◽  
Traffic Conditions ◽  
Adverse Weather ◽  
Approaches To Study ◽  
End To End

Near real-time urban traffic analysis and prediction are paramount for effective intelligent transport systems. Whilst there is a plethora of research on advanced approaches to study traffic recently, only one-third of them has focused on urban arterials. A ready-to-use framework to support decision making in local traffic bureaus using largely available IoT sensors, especially CCTV, is yet to be developed. This study presents an end-to-end urban traffic volume detection and prediction framework using CCTV image series. The framework incorporates a novel Faster R-CNN to generate vehicle counts and quantify traffic conditions. Then it investigates the performance of a statistical-based model (SARIMAX), a machine learning (random forest; RF) and a deep learning (LSTM) model to predict traffic volume 30 min in the future. Tests at six locations with varying traffic conditions under different lengths of past time series are used to train the prediction models. RF and LSTM provided the most accurate predictions, with RF being faster than LSTM. The developed framework has been successfully applied to fill data gaps under adverse weather conditions when data are missing. It can be potentially implemented in near real time at any CCTV location and integrated into an online visualization platform.

scholarly journals Investigation of a Dynamic Power Line Rating Concept for Improved Wind Energy Integration Over Complex Terrain

2014 ◽  
Author(s):  
Tyler B. Phillips ◽  
Inanc Senocak ◽  
Jake P. Gentle ◽  
Kurt S. Myers ◽  
Phil Anderson
Keyword(s):  
Steady State ◽  
Real Time ◽  
Weather Conditions ◽  
Power Line ◽  
Transmission Capacity ◽  
Weather Data ◽  
Energy Integration ◽  
Test Bed ◽  
Worst Case ◽  
Conductor Temperature

Dynamic Line Rating (DLR) is a smart grid technology that allows the rating of power line conductor to be based on its real-time temperature. Currently, conductors are generally given a conservative static rating based on near worst case weather conditions. Using historical weather data collected over a test bed area in Idaho, we demonstrate there is often additional transmission capacity not being utilized under the current static rating practice. We investigate a DLR method that employs computational fluid dynamics (CFD) to determine wind conditions along transmission lines in dense intervals. Simulated wind conditions are then used to calculate real-time conductor temperature under changing weather conditions. In calculating the conductor temperature and then inferring the ampacity, we use both a steady-state and transient calculation procedure. Under low wind conditions, the steady-state assumption predicts higher conductor temperatures which could lead to unnecessary curtailments, whereas the transient calculations produce temperatures that can be significantly lower, implying the availability of additional transmission capacity. Equally important, we demonstrate that capturing the wind direction variability in the simulations is critical in estimating conductor temperatures accurately.

Sign in / Sign up

Export Citation Format

Share Document