Predictive Modeling for Rooftop Solar Energy Throughput: A Machine Learning-Based Optimization for Building Energy Demand Scheduling

2021 ◽  
pp. 1-15
Author(s):  
Mahdi Houchati ◽  
Monem H. Beitelmal ◽  
Marwan Khraisheh
Keyword(s):  
Machine Learning ◽  
Solar Energy ◽  
Energy Demand ◽  
Alternative Energy ◽  
Average Power ◽  
Building Energy ◽  
Prediction Algorithm ◽  
Support Vector ◽  
Solar Photovoltaic ◽  
Photovoltaic Array

Abstract The intermittent and fluctuating nature of solar energy is the biggest challenge facing its widespread utilization. Implementing onsite photovoltaic systems as alternative energy sources have established the need for reliable forecasting procedures to improve scheduling and demand management. This paper presents a solar energy prediction algorithm to optimize the available solar energy resource and manage the demand-side accordingly. The algorithm utilizes Support Vector Regression (SVR), a machine learning technique, validated using 1-year energy consumption data collected from an office building instrumented as an experimental testbed facility. Power meters and temperature sensors collect the building's internal climate and energy data, while a solar photovoltaic array and a weather station provide the external relevant data. The forecasting method uses the average power output of k-similar days as an added input to the SVR model to enhance its performance. The day-ahead prediction results show that this additional input contributes to higher forecasting efficiency, especially in the hot climate regions, where sunny weather conditions prevail throughout the year. The photovoltaic output prediction accuracy for the sunny days is above 90%, which offers possibilities for optimized scheduling and leading to smart building energy management. Finally, this paper also proposes a setpoint optimization algorithm for the building Air Conditioning system to minimize the difference between the building energy load and the generated solar photovoltaic power. Using 24 °C as the upper setpoint temperature limit reduces the energy demand (consumption) by up to 29% and the associated reduction in CO2 emissions.

Model Energi Pembangkit Listrik Tenaga Surya di Pulau Giliyang Madura

2018 ◽  
Vol 2 (2) ◽  
pp. 81
Author(s):  
Nurhadi Nurhadi ◽  
Mochammad Ali M ◽  
Daif Rahuna ◽  
Sutopo P. Fitri
Keyword(s):  
Solar Energy ◽  
Power Systems ◽  
Energy Demand ◽  
Alternative Energy ◽  
Thermal Power ◽  
Electrical Energy ◽  
Solar Photovoltaic ◽  
Solar Panels ◽  
Solar Thermal Power ◽  
Storage Media

Giliiyang Island is a famous island that has the highest oxygen content in the world, and very beautiful sea, but the location is far from PLN / elctictric grid system. It is necessary to develop environmentally friendly alternative energy. One of alternative energy offered is solar energy. Solar energy is energy that’s form of light and heat from the sun. This energy can be utilized using a range of technologies such as solar heating, solar photovoltaic, solar thermal power, solar architecture, and artificial photosynthesis. Based on the calculation is known that the electrical energy demand for Giliiyang Island is around 1984 kWh. The design of two off-grid solar power systems which each capacity about 1 MWp will require 3000 m2 of land with 780 solar panels that have an intensity of 800 W / m2. Deep cycle battery with 24 V DC 200 AH as storage media required about 504 pieces.

Methodology for Optimization of Stand-Alone Solar Photovoltaic Systems

2012 ◽  
Author(s):  
N. Fumo ◽  
V. Bortone ◽  
J. C. Zambrano
Keyword(s):  
Solar Energy ◽  
Energy Demand ◽  
Photovoltaic System ◽  
Design Stage ◽  
Solar Photovoltaic ◽  
Zero Energy ◽  
Photovoltaic Array ◽  
Net Zero Energy ◽  
Net Zero ◽  
Solar Photovoltaic System

The concept of Net-Zero Energy in building refers to a building which has an annual balance of energy flow at the utility meter of zero. The concept implies that the building may consume energy from an external provider at times in order to satisfy the building demands, but at other times it must produce enough on-site energy to compensate for this energy. The use of renewable energy technologies is implicit as the source of energy to compensate for any energy used from an external provider. Solar photovoltaic is a proved technology for achieving Net-Zero Energy building but economic factors has limited its broad use. The design stage of a solar photovoltaic project is critical to make a project feasible. In the design stage, the equipment sizing must be optimized in order to reduce the initial capital cost and, therefore, improve the economics of the project. For houses, which is the focus of this paper, a stand-alone solar photovoltaic system must supply the house energy demand at all times since it is not connected to the electric grid. As a means to size the system, data of solar energy availability must be used to ensure that the system will provide enough energy to satisfy the energy demand as well as provide energy to charge the batteries that will provide the energy required when the solar energy is not available. In this paper, a methodology to optimize the size of the photovoltaic array and the battery bank is proposed. The methodology accounts for Typical Meteorological Year data (TMY3) to ensure that the system, based on accepted statistical data, will be able to satisfy the energy demand at all times. An example that uses energy demand data obtained from the simulation of a house using the software EnergyGauge is used to illustrate the implementation of the methodology.

Uncertainty Analysis for Dimensioning Solar Photovoltaic Arrays

2012 ◽  
Author(s):  
Heejin Cho ◽  
Nelson Fumo
Keyword(s):  
Solar Energy ◽  
Uncertainty Analysis ◽  
Energy Demand ◽  
Fossil Fuels ◽  
Design Stage ◽  
World Population ◽  
Solar Photovoltaic ◽  
Photovoltaic Array ◽  
Photovoltaic Arrays ◽  
Photovoltaic Technology

As the world population increases, so does their demand for energy. The demand of energy is mainly in the form of electricity with an origin primarily from fossil fuels. Since solar photovoltaic technology has the ability to convert solar energy directly into electricity, this technology has become one of the most popular alternatives at all scales for substitution of technology that uses fossil fuels. However, a limiting factor for the massive use solar photovoltaic technology is economics. A key component in the overall strategy to overcome the economic limitation of solar photovoltaic technology is the system size optimization at the design stage. At the design stage, data related to the solar energy availability, energy demand, and equipment performance is used to determine the size of the equipment while being able to satisfy the targeted peak energy demand. In general, a common engineering safety factor is used to ensure the system to meet the energy demand during its life cycle operation. The sizing procedure of solar photovoltaic systems can be further improved to be more reliable and economical when the uncertainty in the design process is considered. This paper presents a framework to perform an uncertainty analysis that can lead to improve sizing process for solar photovoltaic arrays. Through results from the application of the proposed approach, a reliable interval for the size of the photovoltaic array is found that can lead to more accurate and economic design compared to the use of common engineering safety factors.

Solar Photovoltaic Technology—A Review

2020 ◽  
Vol 12 (1) ◽  
pp. 5-10 ◽  
Author(s):  
Praveen Kumar Mishra ◽  
Prabhakar Tiwari
Keyword(s):  
Power Generation ◽  
Solar Energy ◽  
Alternative Energy ◽  
Solar Power ◽  
Solar Photovoltaic ◽  
Tropical Zone ◽  
Renewable Power ◽  
Photovoltaic Technology ◽  
Alternative Sources ◽  
Materials Used

With growing the necessity of alternative energy, this demand will be lead to in the interest of solar research in order to extend the properties containing concentration, charge transfer, absorption and charge separation of solar cell devices along with materials. The solar energy are most abundant, infinite, inexhaustible and clean among all the renewable power resources till now. It can be used by various techniques such as making full use of sunlight to directly generate electricity or by using heat from the sun as a thermal energy. The Photovoltaic technologies are one of the best ways to harness the solar power. The aforementioned one script reviews the photovoltaic technology, its power producing efficiency, the different actual light appealing materials used, its substantial prospect as well various its applications. The Photovoltaic (PV) power generation are one of the most promising power generation among others alternative sources. In this literature survey, we summarize the significance of solar photovoltaic power generation. Solar power generation is likely one of the well-known sectors to give a boost to the sustainability of India. Solar power has giant capability in India due to that it lies in tropical zone. The Solar energy are on the pace to become the fastest rising energy sources in human history.

Evaluation of circulating miRNAs for earlier cancer detection through machine-learning expression profiling.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. 1559-1559
Author(s):  
Jason Chia-Hsun Hsieh ◽  
Chun-Ta Liao ◽  
Hung-Ming Wang ◽  
Ming-Yu Lien ◽  
Yung-Chang Lin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cancer Detection ◽  
Mirna Expression ◽  
Detection System ◽  
Expression Profiles ◽  
Expression Patterns ◽  
Prediction Algorithm ◽  
Support Vector ◽  
Circulating Mirnas ◽  
Cancer Prediction

1559 Background: Earlier cancer diagnosis leads to higher patient survival rate and reduces financial burdens for patients and their families. Over the past five years, liquid biopsy has demonstrated tremendous promise in the early detection of tumor presence. In addition to circulating tumor cells and circulating tumor DNAs, extracellular microRNAs (miRNAs) have also been shown to be promising diagnostic biomarkers. Through machine-learning profiling, we sought to determine whether or not we could use individuals’ miRNA expression to distinguish between healthy subjects and cancer patients. Methods: Blood samples were collected from healthy donors and from patients of various cancer types. Plasma samples were purified within two hours of sample collection, followed by miRNA extraction. After performing reverse transcription of miRNAs into cDNAs, expression analysis of miRNAs was done using a novel multi-gene, amplification-based detection system that simultaneously analyzes over 160 miRNAs. For subsequent data processing, miRNAs without amplification signals across all profiles were first removed, resulting in 135 miRNAs. These 135 resulting miRNAs were then used as features in Support Vector Machine (SVM) to build OncoSweep classifier, a proprietary prediction algorithm for classification of the samples. Ten-fold cross validation was used to evaluate the performance of OncoSweep. Results: 344 healthy donor samples and 417 cancer patient samples were collected for the study. The prediction algorithm, OncoSweep, was derived based on the miRNA expression patterns of the healthy and the patient samples. The algorithm scored an overall accuracy for cancer prediction of 86.47%, with a sensitivity of 91.4%, a specificity of 85%, a PPV of 85% and an NPV of 88.5%. Conclusions: Utilizing machine-learning method of analyzing circulating miRNA expression profiles, the derived algorithm OncoSweep shows significant promise in cancer prediction. Validation is currently being performed in a larger study. We believe circulating miRNAs, through stringent sample processing and machine-learning methodology, are powerful biomarkers for earlier cancer detection.

scholarly journals Machine Learning and Data Segmentation for Building Energy Use Prediction—A Comparative Study

Energies ◽  
2021 ◽  
Vol 14 (18) ◽  
pp. 5947
Author(s):  
William Mounter ◽  
Chris Ogwumike ◽  
Huda Dawood ◽  
Nashwan Dawood
Keyword(s):  
Machine Learning ◽  
Building Energy ◽  
Training Data ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Energy Usage ◽  
Research Attention ◽  
Learning Techniques ◽  
Term Energy

Advances in metering technologies and emerging energy forecast strategies provide opportunities and challenges for predicting both short and long-term building energy usage. Machine learning is an important energy prediction technique, and is significantly gaining research attention. The use of different machine learning techniques based on a rolling-horizon framework can help to reduce the prediction error over time. Due to the significant increases in error beyond short-term energy forecasts, most reported energy forecasts based on statistical and machine learning techniques are within the range of one week. The aim of this study was to investigate how facility managers can improve the accuracy of their building’s long-term energy forecasts. This paper presents an extensive study of machine learning and data processing techniques and how they can more accurately predict within different forecast ranges. The Clarendon building of Teesside University was selected as a case study to demonstrate the prediction of overall energy usage with different machine learning techniques such as polynomial regression (PR), support vector regression (SVR) and artificial neural networks (ANNs). This study further examined how preprocessing training data for prediction models can impact the overall accuracy, such as via segmenting the training data by building modes (active and dormant), or by days of the week (weekdays and weekends). The results presented in this paper illustrate a significant reduction in the mean absolute percentage error (MAPE) for segmented building (weekday and weekend) energy usage prediction when compared to unsegmented monthly predictions. A reduction in MAPE of 5.27%, 11.45%, and 12.03% was achieved with PR, SVR and ANN, respectively.

scholarly journals A machine-learning approach to predict postprandial hypoglycemia

2019 ◽  
Vol 19 (1) ◽  
Author(s):  
Wonju Seo ◽  
You-Bin Lee ◽  
Seunghyun Lee ◽  
Sang-Man Jin ◽  
Sung-Min Park
Keyword(s):  
Machine Learning ◽  
Nearest Neighbor ◽  
Learning Algorithm ◽  
Characteristic Curve ◽  
Artificial Pancreas ◽  
Individual Performance ◽  
Machine Learning Algorithms ◽  
Prediction Algorithm ◽  
Support Vector ◽  
K Nearest Neighbor

Abstract Background For an effective artificial pancreas (AP) system and an improved therapeutic intervention with continuous glucose monitoring (CGM), predicting the occurrence of hypoglycemia accurately is very important. While there have been many studies reporting successful algorithms for predicting nocturnal hypoglycemia, predicting postprandial hypoglycemia still remains a challenge due to extreme glucose fluctuations that occur around mealtimes. The goal of this study is to evaluate the feasibility of easy-to-use, computationally efficient machine-learning algorithm to predict postprandial hypoglycemia with a unique feature set. Methods We use retrospective CGM datasets of 104 people who had experienced at least one hypoglycemia alert value during a three-day CGM session. The algorithms were developed based on four machine learning models with a unique data-driven feature set: a random forest (RF), a support vector machine using a linear function or a radial basis function, a K-nearest neighbor, and a logistic regression. With 5-fold cross-subject validation, the average performance of each model was calculated to compare and contrast their individual performance. The area under a receiver operating characteristic curve (AUC) and the F1 score were used as the main criterion for evaluating the performance. Results In predicting a hypoglycemia alert value with a 30-min prediction horizon, the RF model showed the best performance with the average AUC of 0.966, the average sensitivity of 89.6%, the average specificity of 91.3%, and the average F1 score of 0.543. In addition, the RF showed the better predictive performance for postprandial hypoglycemic events than other models. Conclusion In conclusion, we showed that machine-learning algorithms have potential in predicting postprandial hypoglycemia, and the RF model could be a better candidate for the further development of postprandial hypoglycemia prediction algorithm to advance the CGM technology and the AP technology further.

scholarly journals Forecasting Solar PV Demand Split and Fuel Wood Usage Reduction in Eriti and Oke-Agunla Villages in Nigeria

2020 ◽  
pp. 45-60
Author(s):  
Olalekan Aquila Jesuleye
Keyword(s):  
Total Energy ◽  
Rural Areas ◽  
Energy Demand ◽  
Alternative Energy ◽  
Solar Photovoltaic ◽  
Solar Pv ◽  
Fuel Wood ◽  
Household Data ◽  
Alternative Energy Sources ◽  
Local Dialect

The study examined solar photovoltaic demand split and fuel wood usage reduction in Eriti and Oke-Agunla villages, that were among the pilot sites for solar electrification programs in the western ecological region of Nigeria. It used questionnaire techniques to elicit information in the local dialect of the respondents, on alternative energy sources for provision of energy services from each of the household's heads, representing solar PV users, in all the 371 households that constitute about 13.4 percent of the 2,778 dwellers in the two villages, for the base year 2020. Specifically, at the rate of the observed 8 dwellers per household, data were obtained from 179 respondents, out of a total of 1,434 dwellers in Eriti village. Likewise, at the rate of the observed 7 dwellers per household, data were also obtained from 192 respondents, out of a total of 1,344 dwellers in Oke-Agunla village. Model for Analysis of Energy Demand (MADE-II) was used for the study. The study showed that the total lighting demand share for solar PV in each of the villages’ total energy demand mix in 2020 was insignificantly low at 5.1 percent share in Eriti village and 6.1 percent share in Oke-Agunla village. Contrariwise, firewood demand maintained as high as 94 and 92 percent share for Eriti and Oke-Agunla villages respectively in the total energy demand mix and by 2030, in Oke-Agunla village, 3-stones-firewood stoves demand for cooking fell drastically from 77% to 30% share, whereas improved firewood stoves demand for cooking rose astronomically from 11% share in 2020 to 45% share by 2030. Nigerian government should adopt such best policy intervention scenario for all the rural areas in the country.

scholarly journals Simulation and Modeling of a Five -Level (NPC) Inverter Fed by a Photovoltaic Generator and Integrated in a Hybrid Wind-PV Power System

2017 ◽  
Vol 7 (4) ◽  
pp. 1759-1764
Author(s):  
M. Rezki ◽  
I. Griche
Keyword(s):  
Power System ◽  
Energy Demand ◽  
Alternative Energy ◽  
Good Alternative ◽  
Industrial Applications ◽  
Solar Photovoltaic ◽  
Simulation And Modeling ◽  
Wind Power System ◽  
Coal Reserves ◽  
Inverter Topology

A distributed hybrid coordinated wind photovoltaic (PV) power system was proposed in this paper. As oil and coal reserves are being depleted whilst at the same time the energy demand is growing, it is important to consider alternative energy generating techniques. Today, the five-level (NPC) inverter represents a good alternative for several industrial applications. To take advantage of the five-level inverter topology and the benefits of renewable energy represented by a photovoltaic generator, a new scheme of these controllers is proposed in this work. This paper outlines the design of a hybrid power system consisting of a solar photovoltaic (PV) and a wind power system. The system is modeled in Matlab Simulink and tested for various conditions. The model and results are discussed in this paper.

scholarly journals Estimation of Room-Level Cooling Energy in Hot/Arid Climate by Machine Learning-Based Approaches

2021 ◽  
Author(s):  
Bingyan Jia ◽  
Danlin Hou ◽  
Liangzhu (Leon) Wang ◽  
Ibrahim Galal Hassan
Keyword(s):  
Machine Learning ◽  
Power Density ◽  
Mean Squared Error ◽  
Building Energy ◽  
Energy Performance ◽  
Mean Bias Error ◽  
Support Vector ◽  
Bias Error ◽  
Model Parameters ◽  
Meta Model

Abstract Building energy models (BEM) are developed for understanding a building’s energy performance. A meta-model of the whole building energy analysis is often used for the BEM calibration and energy prediction. The literature review shows that studies with a focus on the development of room-level meta-models are missing. This study aims to address this research gap through a case study of a residential building with 138 apartments in Doha, Qatar. Five parameters, including cooling setpoint, number of occupants, lighting power density, equipment power density, and interior solar reflectance, are selected as input parameters to create ninety-six different scenarios. Three machine-learning models are used as meta-models to generalize the relationship between cooling energy and the model parameters, including Multiple Linear Regression, Support Vector Regression, and Artificial Neural Networks. The three meta-models’ prediction accuracies are evaluated by the Normalized Mean Bias Error (NMBE), Coefficient of Variation of the Root Mean Squared Error CV (RMSE), and R square (R2). The results show that the ANN model performs best. A new generic BEM is then established to validate the meta-model. The results indicate that the proposed meta-model is accurate and efficient in predicting the cooling energy in summer and transitional months for a building with a similar floor configuration.

Sign in / Sign up

Export Citation Format

Share Document