CT-NET: A Novel Convolutional Transformer-Based Network for Short-Term Solar Energy Forecasting Using Climatic Information

Photovoltaic(PV)systems are environmentally friendly,generate green energy,and receive support from policies and organizations.However,weather fluctuations make large-scale PV power integration and management challenging despite the economic benefits.Existing PV forecasting techniques(sequential and convolutional neural networks(CNN))are sensitive to environmental conditions,reducing energy distribution system performance.To handle these issues,this article proposes an efficient,weather-resilient convolutional-transformer-based network(CT-NET)for accurate and efficient PV power forecasting.The network consists of three main modules.First,the acquired PV generation data are forwarded to the pre-processing module for data refinement.Next,to carry out data encoding,a CNNbased multi-head attention(MHA)module is developed in which a single MHA is used to decode the encoded data.The encoder module is mainly composed of 1D convolutional and MHA layers,which extract local as well as contextual features,while the decoder part includes MHA and feedforward layers to generate the final prediction.Finally,the performance of the proposed network is evaluated using standard error metrics,including the mean squared error(MSE),root mean squared error(RMSE),and mean absolute percentage error(MAPE).An ablation study and comparative analysis with several competitive state-of-the-art approaches revealed a lower error rate in terms of MSE(0.0471),RMSE(0.2167),and MAPE(0.6135)over publicly available benchmark data.In addition,it is demonstrated that our proposed model is less complex,with the lowest number of parameters(0.0135 M),size(0.106 MB),and inference time(2 ms/step),suggesting that it is easy to integrate into the smart grid.

Short-Term Wind Energy Forecasting Using Deep Learning-Based Predictive Analytics

Wind energy is featured by instability due to a number of factors,such as weather,season,time of the day,climatic area and so on.Furthermore,instability in the generation of wind energy brings new challenges to electric power grids,such as reliability,flexibility,and power quality.This transition requires a plethora of advanced techniques for accurate forecasting of wind energy.In this context,wind energy forecasting is closely tied to machine learning(ML)and deep learning(DL)as emerging technologies to create an intelligent energy management paradigm.This article attempts to address the short-term wind energy forecasting problem in Estonia using a historical wind energy generation data set.Moreover,we taxonomically delve into the state-of-the-art ML and DL algorithms for wind energy forecasting and implement different trending ML and DL algorithms for the day-ahead forecast.For the selection of model parameters,a detailed exploratory data analysis is conducted.All models are trained on a real-time Estonian wind energy generation dataset for the first time with a frequency of 1 h.The main objective of the study is to foster an efficient forecasting technique for Estonia.The comparative analysis of the results indicates that Support Vector Machine(SVM),Non-linear Autoregressive Neural Networks(NAR),and Recurrent Neural Network-Long-Term Short-Term Memory(RNNLSTM)are respectively 10%,25%,and 32%more efficient compared to TSO’s forecasting algorithm.Therefore,RNN-LSTM is the best-suited and computationally effective DL method for wind energy forecasting in Estonia and will serve as a futuristic solution.

Enhancing photovoltaic energy forecasting:a progressive approach using wavelet packet decomposition

Accurate photovoltaic(PV)energy forecasting plays a crucial role in the efficient operation of PV power stations.This study presents a novel hybrid machine-learning(ML)model that combines Gaussian process regression with wavelet packet decomposition to forecast PV power half an hour ahead.The proposed technique was applied to the PV energy database of a station located in Algeria and its performance was compared to that of traditional forecasting models.Performance evaluations demonstrate the superiority of the proposed approach over conventional ML methods,including Gaussian process regression,extreme learning machines,artificial neural networks and support vector machines,across all seasons.The proposed model exhibits lower normalized root mean square error(nRMSE)(2.116%)and root mean square error(RMSE)(208.233 kW)values,along with a higher coefficient of determination(R^(2))of 99.881%.Furthermore,the exceptional performance of the model is maintained even when tested with various prediction horizons.However,as the forecast horizon extends from 1.5 to 5.5 hours,the prediction accuracy decreases,evident by the increase in the RMSE(710.839 kW)and nRMSE(7.276%),and a decrease in R2(98.462%).Comparative analysis with recent studies reveals that our approach consistently delivers competitive or superior results.This study provides empirical evidence supporting the effectiveness of the proposed hybrid ML model,suggesting its potential as a reliable tool for enhancing PV power forecasting accuracy,thereby contributing to more efficient grid management.

An artificial intelligence framework for explainable drift detection in energy forecasting

Accurate energy consumption forecasting is crucial for reducing operational costs, achieving net-zero carbon emissions, and ensuring sustainable buildings and cities of the future. Despite the frequent use of Artificial Intelligence (AI) algorithms for learning energy consumption patterns and predictions in Building Science, relying solely on these techniques for energy demand prediction addresses only a fraction of the challenge. A drift in energy usage can lead to inaccuracies in these AI models and subsequently to poor decision-making and interventions. While drift detection techniques have been reported, a reliable and robust approach capable of explaining identified discrepancies with actionable insights has not been discussed in extant literature. Hence, this paper presents an Artificial Intelligence framework for energy consumption forecasting with explainable drift detection, aimed at addressing these challenges. The proposed framework is composed of energy embeddings, an optimized dimensional model integrated within a data warehouse, and scalable cloud implementation for effective drift detection with explainability capability. The framework is empirically evaluated in the real-world setting of a multi-campus, mixed-use tertiary education setting in Victoria, Australia. The results of these experiments highlight its capabilities in detecting concept drift, adapting forecast predictions, and providing an interpretation of the changes using energy embeddings.

Residential Energy Consumption Forecasting Based on Federated Reinforcement Learning with Data Privacy Protection

Most studies have conducted experiments on predicting energy consumption by integrating data formodel training.However, the process of centralizing data can cause problems of data leakage.Meanwhile,many laws and regulationson data security and privacy have been enacted, making it difficult to centralize data, which can lead to a datasilo problem. Thus, to train the model while maintaining user privacy, we adopt a federated learning framework.However, in all classical federated learning frameworks secure aggregation, the Federated Averaging (FedAvg)method is used to directly weight the model parameters on average, which may have an adverse effect on te model.Therefore, we propose the Federated Reinforcement Learning (FedRL) model, which consists of multiple userscollaboratively training the model. Each household trains a local model on local data. These local data neverleave the local area, and only the encrypted parameters are uploaded to the central server to participate in thesecure aggregation of the global model. We improve FedAvg by incorporating a Q-learning algorithm to assignweights to each locally uploaded local model. And the model has improved predictive performance. We validatethe performance of the FedRL model by testing it on a real-world dataset and compare the experimental results withother models. The performance of our proposed method in most of the evaluation metrics is improved comparedto both the centralized and distributed models.

Adaptive Error Curve Learning Ensemble Model for Improving Energy Consumption Forecasting

Despite the advancement within the last decades in the field of smart grids,energy consumption forecasting utilizing the metrological features is still challenging.This paper proposes a genetic algorithm-based adaptive error curve learning ensemble(GA-ECLE)model.The proposed technique copes with the stochastic variations of improving energy consumption forecasting using a machine learning-based ensembled approach.A modified ensemble model based on a utilizing error of model as a feature is used to improve the forecast accuracy.This approach combines three models,namely CatBoost(CB),Gradient Boost(GB),and Multilayer Perceptron(MLP).The ensembled CB-GB-MLP model’s inner mechanism consists of generating a meta-data from Gradient Boosting and CatBoost models to compute the final predictions using the Multilayer Perceptron network.A genetic algorithm is used to obtain the optimal features to be used for the model.To prove the proposed model’s effectiveness,we have used a four-phase technique using Jeju island’s real energy consumption data.In the first phase,we have obtained the results by applying the CB-GB-MLP model.In the second phase,we have utilized a GA-ensembled model with optimal features.The third phase is for the comparison of the energy forecasting result with the proposed ECL-based model.The fourth stage is the final stage,where we have applied the GA-ECLE model.We obtained a mean absolute error of 3.05,and a root mean square error of 5.05.Extensive experimental results are provided,demonstrating the superiority of the proposed GA-ECLE model over traditional ensemble models.

A review and taxonomy of wind and solar energy forecasting methods based on deep learning

Renewable energy is essential for planet sustainability.Renewable energy output forecasting has a significant impact on making decisions related to operating and managing power systems.Accurate prediction of renewable energy output is vital to ensure grid reliability and permanency and reduce the risk and cost of the energy market and systems.Deep learning’s recent success in many applications has attracted researchers to this field and its promising potential is manifested in the richness of the proposed methods and the increasing number of publications.To facilitate further research and development in this area,this paper provides a review of deep learning-based solar and wind energy forecasting research published during the last five years discussing extensively the data and datasets used in the reviewed works,the data pre-processing methods,deterministic and probabilistic methods,and evaluation and comparison methods.The core characteristics of all the reviewed works are summarised in tabular forms to enable methodological comparisons.The current challenges in the field and future research directions are given.The trends show that hybrid forecasting models are the most used in this field followed by Recurrent Neural Network models including Long Short-Term Memory and Gated Recurrent Unit,and in the third place Convolutional Neural Networks.We also find that probabilistic and multistep ahead forecasting methods are gaining more attention.Moreover,we devise a broad taxonomy of the research using the key insights gained from this extensive review,the taxonomy we believe will be vital in understanding the cutting-edge and accelerating innovation in this field.

Caribbean Sea Offshore Wind Energy Assessment and Forecasting

The exploitation of wind energy is rapidly evolving and is manifested in the ever-expanding global network of offshore wind energy farms.For the Small Island Developing States of the Caribbean Sea(CS),harnessing this mature technology is an important first step in the transition away from fossil fuels.This paper uses buoy and satellite observations of surface wind speed in the CS to estimate wind energy resources over the 2009–201911-year period and initiates hour-ahead forecasting using the long short-term memory(LSTM)network.Observations of wind power density(WPD)at the 100-m height showed a mean of approximately 1000 W/m^(2) in the Colombia Basin,though this value decreases radially to 600–800 W/m^(2) in the central CS to a minimum of approximately 250 W/m^(2) at its borders in the Venezuela Basin.The Caribbean Low-Level Jet(CLLJ)is also responsible for the waxing and waning of surface wind speed and as such,resource stability,though stable as estimated through monthly and seasonal coefficients of variation,is naturally governed by CLLJ activity.Using a commercially available offshore wind turbine,wind energy generation at four locations in the CS is estimated.Electricity production is greatest and most stable in the central CS than at either its eastern or western borders.Wind speed forecasts are also found to be more accurate at this location,and though technology currently restricts offshore wind turbines to shallow water,outward migration to and colonization of deeper water is an attractive option for energy exploitation.

Hybrid LEAP modeling method for long-term energy demand forecasting of regions with limited statistical data

An accurate long-term energy demand forecasting is essential for energy planning and policy making. However, due to the immature energy data collecting and statistical methods, the available data are usually limited in many regions. In this paper, on the basis of comprehensive literature review, we proposed a hybrid model based on the long-range alternative energy planning (LEAP) model to improve the accuracy of energy demand forecasting in these regions. By taking Hunan province, China as a typical case, the proposed hybrid model was applied to estimating the possible future energy demand and energy-saving potentials in different sectors. The structure of LEAP model was estimated by Sankey energy flow, and Leslie matrix and autoregressive integrated moving average (ARIMA) models were used to predict the population, industrial structure and transportation turnover, respectively. Monte-Carlo method was employed to evaluate the uncertainty of forecasted results. The results showed that the hybrid model combined with scenario analysis provided a relatively accurate forecast for the long-term energy demand in regions with limited statistical data, and the average standard error of probabilistic distribution in 2030 energy demand was as low as 0.15. The prediction results could provide supportive references to identify energy-saving potentials and energy development pathways.

Overview of the Global Electricity System in Oman Considering Energy Demand Model Forecast

Lately,in modern smart power grids,energy demand for accurate forecast of electricity is gaining attention,with increased interest of research.This is due to the fact that a good energy demand forecast would lead to proper responses for electricity demand.In addition,proper energy demand forecast would ensure efficient planning of the electricity industry and is critical in the scheduling of the power grid capacity and management of the entire power network.As most power systems are been deregulated and with the rapid introduction and development of smart-metering technologies in Oman,new opportunities may arise considering the efficiency and reliability of the power system;like price-based demand response programs.These programs could either be a large scale for household,commercial or industrial users.However,excellent demand forecasting models are crucial for the deployment of these smart metering in the power grid based on good knowledge of the electricity market structure.Consequently,in this paper,an overview of the Oman regulatory regime,financial mechanism,price control,and distribution system security standard were presented.More so,the energy demand forecast in Oman was analysed,using the econometric model to forecasts its energy peak demand.The energy econometric analysis in this study describes the relationship between the growth of historical electricity consumption and macro-economic parameters(by region,and by tariff),considering a case study of Mazoon Electricity Distribution Company(MZEC),which is one of the major power distribution companies in Oman,for effective energy demand in the power grid.

End-to-end data-driven modeling framework for automated and trustworthy short-term building energy load forecasting

Conventional automated machine learning(AutoML)technologies fall short in preprocessing low-quality raw data and adapting to varying indoor and outdoor environments,leading to accuracy reduction in forecasting short-term building energy loads.Moreover,their predictions are not transparent because of their black box nature.Hence,the building field currently lacks an AutoML framework capable of data quality enhancement,environment self-adaptation,and model interpretation.To address this research gap,an improved AutoML-based end-to-end data-driven modeling framework is proposed.Bayesian optimization is applied by this framework to find an optimal data preprocessing process for quality improvement of raw data.It bridges the gap where conventional AutoML technologies cannot automatically handle missing data and outliers.A sliding window-based model retraining strategy is utilized to achieve environment self-adaptation,contributing to the accuracy enhancement of AutoML technologies.Moreover,a local interpretable model-agnostic explanations-based approach is developed to interpret predictions made by the improved framework.It overcomes the poor interpretability of conventional AutoML technologies.The performance of the improved framework in forecasting one-hour ahead cooling loads is evaluated using two-year operational data from a real building.It is discovered that the accuracy of the improved framework increases by 4.24%–8.79%compared with four conventional frameworks for buildings with not only high-quality but also low-quality operational data.Furthermore,it is demonstrated that the developed model interpretation approach can effectively explain the predictions of the improved framework.The improved framework offers a novel perspective on creating accurate and reliable AutoML frameworks tailored to building energy load prediction tasks and other similar tasks.

An Accurate Dynamic Forecast of Photovoltaic Energy Generation

The accurate forecast of the photovoltaic generation(PVG)process is essential to develop optimum installation sizing and pragmatic energy planning and management.This paper proposes a PVG forecast model for a PVG/Battery installation.The forecasting strategy is built on a Medium-Term Energy Forecasting(MTEF)approach refined dynamically every hour(Dynamic Medium-Term Energy Forecasting(DMTEF))and adjusted by means of a Short-Term Energy Forecasting(STEF)strategy.The MTEF predicts the generated energy for a day ahead based on the PVG of the last 15 days.As for STEF,it is a combination between PVG Short-Term(ST)forecasting and DMTEF methods obtained by selecting the least inaccurate PVG estimation every 15 minutes.The algorithm results are validated by measures taken on a 3 KWp standalone PVG/Battery installation.The proposed approaches have been integrated into a management algorithm in order to make a pragmatic decision to ensure load supply considering relevant constraints and priorities and guarantee the battery safety.Simulation results show that STEF provides accurate results compared to measures in stable and perturbed days.The NMBE(Normalized Mean Bias Error)is equal to-0.58%in stable days and 26.10%in perturbed days.

Statistical Analysis and Energy Planning of Electric Power Supply Systems with Intelligent Control

The study presents possibilities for reconstruction of electric power supply systems in Bulgarian Black Sea resorts and possibilities to use statistical methods in energy planning. The paper shows the use of classic statistical methods in combination with advanced digital measurement systems in order to obtain the correlation dependencies, nature of energy consumption and opportunities for energy forecasting. The main purpose of the study is to obtain statistical dependencies of the nature of power consumption and correlations between electricity consumption and ambient temperature in order to improve the accuracy of energy planning. The analysis includes application of energy management systems for proper energy planning, improving economical efficiency and reducing power and energy losses.

Forecasting of China's natural gas production and its policy implications

With the vigorous promotion of energy conservation and implementation of clean energy strategies,China＇s natural gas industry has entered a rapid development phase,and natural gas is playing an increasingly important role in China＇s energy structure.This paper uses a Generalized Weng model to forecast Chinese regional natural gas production,where accuracy and reasonableness compared with other predictions are enhanced by taking remaining estimated recoverable resources as a criterion.The forecast shows that China＇s natural gas production will maintain a rapid growth with peak gas of 323 billion cubic meters a year coming in 2036;in 2020,natural gas production will surpass that of oil to become a more important source of energy.Natural gas will play an important role in optimizing China＇s energy consumption structure and will be a strategic replacement of oil.This will require that exploration and development of conventional natural gas is highly valued and its industrial development to be reasonably planned.As well,full use should be made of domestic and international markets.Initiative should also be taken in the exploration and development of unconventional and deepwater gas,which shall form a complement to the development of China＇s conventional natural gas industry.

Our Daily Life Dependency Driven by Renewable and Nonrenewable Source of Energy

Our dependency on energy is so vital that it makes it difficult to imagine how humans can live on our planet earth without it.The demand for electricity,for example,is directly related to the growth of the population worldwide,and presently,to meet this demand,we need both renewable and nonrenewable energy.While nonrenewable energy has its shortcomings(negative impact on climate change,for example),renewable energy is not enough to address the ever-changing demand for energy.One way to address this need is to become more innovative,use technology more effectively,and be aware of the costs associated with different sources of renewable energy.In the case of nuclear power plants,new innovative centered around small modular reactors(SMRs)of generation 4th of these plants make them safer and less costly to own them as well as to protect them via means of cyber-security against any attack by smart malware.Of course,understanding the risks and how to address them is an integral part of the study.Natural sources of energy,such as wind and solar,are suggesting other innovating technical approaches.In this article,we are studying these factors holistically,and details have been laid out in a book by the authors’second volume of series title as Knowledge Is Power in Four Dimensions under Energy subtitle.

Adaptive meta-learning extreme learning machine with golden eagle optimization and logistic map for forecasting the incomplete data of solar iradiance

Solar energy has become crucial in producing electrical energy because it is inexhaustible and sustainable.However,its uncertain generation causes problems in power system operation.Therefore,solar irradiance forecasting is significant for suitable controlling power system operation,organizing the transmission expansion planning,and dispatching power system generation.Nonetheless,the forecasting performance can be decreased due to the unfitted prediction model and lacked preprocessing.To deal with mentioned issues,this paper pro-poses Meta-Learning Extreme Learning Machine optimized with Golden Eagle Optimization and Logistic Map(MGEL-ELM)and the Same Datetime Interval Averaged Imputation algorithm(SAME)for improving the fore-casting performance of incomplete solar irradiance time series datasets.Thus,the proposed method is not only imputing incomplete forecasting data but also achieving forecasting accuracy.The experimental result of fore-casting solar irradiance dataset in Thailand indicates that the proposed method can achieve the highest coeffi-cient of determination value up to 0.9307 compared to state-of-the-art models.Furthermore,the proposed method consumes less forecasting time than the deep learning model.

Impact of household transitions on domestic energy consumption and its applicability to urban energy planning

The household sector consumes roughly 30% of Earth's energy resources and emits approximately 17% of its carbon dioxide. As such, developing appropriate policies to reduce the CO_2 emissions, which are associated with the world's rapidly growing urban population, is a high priority. This, in turn, will enable the creation of cities that respect the natural environment and the well-being of future generations. However, most of the existing expertise focuses on enhancing the thermal quality of buildings through building physics while few studies address the social and behavioral aspects. In fact, focusing on these aspects should be more prominent, as they cause between 4% and 30% of variation in domestic energy consumption.Premised on that, the aim of this study was to investigate the effect in the context of the UK of household transitions on household energy consumption patterns. To achieve this, we applied statistical procedures(e.g., logistic regression) to official panel survey data comprising more than 5500 households in the UK tracked annually over the course of 18 years. This helped in predicting future transition patterns for different household types for the next 10 to 15 years. Furthermore, it enabled us to study the relationship between the predicted patterns and the household energy usage for both gas and electricity. The findings indicate that the life cycle transitions of a household significantly influence its domestic energy usage. However, this effect is mostly positive in direction and weak in magnitude. Finally, we present our developed urban energy model "Evo Energy" to demonstrate the importance of incorporating such a concept in energy forecasting for effective sustainable energy decision-making.

An analysis of the correlation between the fluxes of high-energy electrons and low-middle-energy electrons in the magnetosphere

The variation of the flux of energetic electrons in the magnetosphere has been proven to be strongly related to the solar wind speed. Observations of GEO orbit show that the flux of low-energy electrons is not only modulated by the solar wind speed, but, if a time delay is added, is also positively correlated to the flux of high-energy electrons. This feature provides a possible method to forecast the flux of high-energy electrons in GEO orbit. In this study, the correlations of the fluxes between the high-energy electrons and low-middle-energy electrons obtained at different L values and in different orbits are investigated to develop the application of this feature. Based on the analysis of long–term data observed by NOAA POES and GOES, the correlations between the fluxes of high-energy electrons and low–middle–energy electrons are good enough at different L values and in different orbits in quiet time, but this correlation is strongly affected by CME–driven geomagnetic storms.

Prediction of End-Use Energy Consumption in a Region of Northwest China

End-use energy consumption can reflect the industrial development of a country and the living standards of its residents. The study of end-use energy consumption can provide a solid basis for industrial restructuring, energy saving, and emission reduction. In this paper, we analyzed the end-use energy consumption of a region in Northwestern China, and applied the Markov prediction method to forecast the future demand of different types of end-use energy. This provides a reference for the energy structure optimization in the Northwestern China.

Energy Management System Design and Testing for Smart Buildings Under Uncertain Generation (Wind/Photovoltaic) and Demand

This study provides details of the energy management architecture used in the Goldwind microgrid test bed. A complete mathematical model, including all constraints and objectives, for microgrid operational management is first described using a modified prediction interval scheme. Forecasting results are then achieved every 10 min using the modified fuzzy prediction interval model, which is trained by particle swarm optimization.A scenario set is also generated using an unserved power profile and coverage grades of forecasting to compare the feasibility of the proposed method with that of the deterministic approach. The worst case operating points are achieved by the scenario with the maximum transaction cost. In summary, selection of the maximum transaction operating point from all the scenarios provides a cushion against uncertainties in renewable generation and load demand.