Dynamic Forecasting of Solar Energy Microgrid Systems Using Feature Engineering

Mohamed, Muamar; Mahmood, Farhad E.; Mehmmood, A.; Chandra, Ambrish; Singh, Bhim

doi:10.1109/tia.2022.3199182

Cited by 20 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, Bayesian Information Criterion (BIC) was a basic criterion for choosing the best fit of the ARIMA (p, d, q) model. Mohamed et al [24] proposed the formula BIC = k ln(n) − 2ln(L), which is easier to deal with BIC.…”

Section: Resource Forecasting By Time Series Modeling (Arima)mentioning

confidence: 99%

Source Forecasting and Economic/Environmental Assessment of Hybrid Renewable Energy System in North Eastern State of India

Komanapalli,

Mansani,

Hampannavar

et al. 2024

Preprint

View full text Add to dashboard Cite

Clean and sustainable energy holds preeminent importance from a socio-environmental standpoint and can be achieved through the implementation of a Hybrid Renewable Energy System (HRES). As well as ensuring the stable and reliable operation of power systems amidst the increasing integration of renewable energy sources, precise source forecasting becomes indispensable. Thus, this paper presents a pioneering HRES design incorporating Photovoltaic (PV), Wind Turbine (WT), and Biogas Generator (Bio) technologies, wherein animal manure is utilized as biomass for the sustainable valorization of animal waste. The preliminary objective of this study is to address the prevailing gaps to attain sustainable energy production that is both cost-optimal and technically efficient. Consequently, this paper investigates source forecasting through time series modeling, and assesses the techno-environmental and economic viability of HRES (both off-grid and on-grid) within the northeastern state of India, specifically focusing on the case study of the Cachar district in Assam state. Moreover, real data analysis is conducted to model and optimize the hybrid system. The findings reveal promising outcomes in terms of cost, emissions, and electrical energy potential, which are presented and comprehensively discussed. Furthermore, a sensitivity analysis is performed to assess the system's robustness. The analyzed results are compared and validated with existing literature including different energy economics with optimum configurations. Finally, this study endeavors to project a future power system for one of the prominent regions in Assam, an Indian state.

show abstract

Section: Resource Forecasting By Time Series Modeling (Arima)mentioning

confidence: 99%

Source Forecasting and Economic/Environmental Assessment of Hybrid Renewable Energy System in North Eastern State of India

Komanapalli,

Mansani,

Hampannavar

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Gradient boosting is an ensemble machine learning technique that combines multiple weak prediction learners. In this paper, we utilise light gradient boosted machine (LightGBM) framework to implement QR for negative price forecasting [14]. LightGBM supports faster training with the help of parallel and distributed learning module in it.…”

Section: B Gradient Boosting Using Lightgbmmentioning

confidence: 99%

Negative Price Forecasting in Australian Energy Markets using gradient-boosted Machines: Predictive and Probabilistic Analysis

Kaur,

Aujla,

Mahmud

2023

2023 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)

View full text Add to dashboard Cite

With the integration of distributed energy resources such as roof-top solar panels and wind turbines into the grid, power generation can surpass demand-generation and thus, gives rise to the negative pricing events, especially during summer months. In this regard, a scientific case study is conducted in this paper to analyse and predict the increasing instances of negative energy prices against demand-generation in Australian energy markets (AEMs) using real-time energy data from the Hornsdale power reserve, South Australia. A robust machine learning method, Light gradient boosting machine (LightGBM) is utilised to detect and predict negative prices at different quantiles to quantify the outliers in the pricing data. The implementation results demonstrate that predicting the prices at different quantiles can tackle outliers (negative prices) effectively with the help of extracted upper and lower bounds using quantile regression-based approach. The case study is further extended to learn the complex statistical relationships between different data features using Naive-Bayes Tree Augmented (NB-TAN) algorithm considering 'price' as the dependent feature against the independent features such as demand-generation, battery charging/discharging, and frequency control ancillary services.

show abstract

“…By integrating UPQC into the tariff rate forecasting model, we not only enhance the precision of our predictions but also address the real-time power quality challenges that can impact microgrid operations [11]. This fusion of technologies promises more reliable energy management and decisionmaking within microgrids, ensuring that they can adapt to dynamic supply and demand conditions while maintaining optimal power quality standards [12].…”

Section: Introductionmentioning

confidence: 99%

Forecasting Tariff Rates and Enhancing Power Quality in Microgrids: The Synergistic Role of LSTM and UPQC

Sahoo,

Swain,

Dash

et al. 2024

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

The current paper presents an original approach into the microgrid control framework by incorporating LSTM-based optimization with specific emphasis on refining the gain parameters of a Proportional-Integral-Derivative (PID) controller. This integration represents a significant advancement in improving the overall efficiency of microgrid control systems. By creatively applying LSTM optimization, the paper achieves dynamic adjustments of the PID controller's parameters, resulting in more precise regulation of output power quality. Through the utilization of the Unified Power Quality Conditioner (UPQC) in conjunction with LSTM-based optimization, the paper establishes a compelling link between improved power quality and the resultant tariff rates. This highlights their combined influence on enhancing power quality and calibrating tariff rates, providing a fresh perspective on optimizing microgrid operations.

show abstract

Dynamic Forecasting of Solar Energy Microgrid Systems Using Feature Engineering

Cited by 20 publications

References 32 publications

Source Forecasting and Economic/Environmental Assessment of Hybrid Renewable Energy System in North Eastern State of India

Source Forecasting and Economic/Environmental Assessment of Hybrid Renewable Energy System in North Eastern State of India

Negative Price Forecasting in Australian Energy Markets using gradient-boosted Machines: Predictive and Probabilistic Analysis

Forecasting Tariff Rates and Enhancing Power Quality in Microgrids: The Synergistic Role of LSTM and UPQC

Contact Info

Product

Resources

About