Search

Deep learning models in recent times have shown promising results for solar energy forecasting. Solar energy depends heavily on local weather conditions, and as a result, typically hundreds of models are built, which need site and season-specific training. The model maintenance and management also become a tedious job with such a large number of models. Here, we are motivated to use transfer learning to accommodate local variations in the solar pattern over the available global pattern. It may also be noted that apparently transfer learning has been rarely/never used for solar forecasting. In this paper, we have proposed a bidirectional gated recurrent unit (BGRU) based model, which employs transfer learning for short-term solar energy forecasting. The said model yields better forecasting accuracy compared to site-specific models with a lower variance. It also takes 39.6% less parameters and 76.1% reduced time for training. The current literature suggests that selection of base scenario for transfer learning is an open problem and in this paper, we have also proposed an intuitive strategy for the same. The effectiveness of the same is established through empirical study. [ABSTRACT FROM AUTHOR]

Short-term electric power load forecasting is a critical and essential task for utilities in the electric power industry for proper energy trading, which enables the independent system operator to operate the network without any technical and economical issues. From an electric power distribution system point of view, accurate load forecasting is essential for proper planning and operation. In order to build most robust machine learning model to forecast the load with a good accuracy irrespective of weather condition and type of day, features such as the season, temperature, humidity and day-status are incorporated into the data. In this paper, a machine learning model, namely a regression tree, is used to forecast the active power load an hour and one day ahead. Real-time active power load data to train and test the machine learning models are collected from a 33/11 kV substation located in Telangana State, India. Based on the simulation results, it is observed that the regression tree model is able to forecast the load with less error. [ABSTRACT FROM AUTHOR]

With ambitious renewable energy capacity addition targets, there is an ongoing transformation in the Indian power system. This paper discusses the various applications of variable generation forecast, state-of-the-art solar PV generation forecasting methods, latest developments in generation forecasting regulations and infrastructure, and the new challenges introduced by VRE generation. Day-ahead NWP-based GHI forecasting are validated against ground measurements from single and multiple sites in India. Recommendations for improving overall the forecasting infrastructure in India are presented. [ABSTRACT FROM AUTHOR]

Electricity is an essential commodity that must be generated in response to demand. Hydroelectric power plants, fossil fuels, nuclear energy, and wind energy are just a few examples of energy sources that significantly impact production costs. Accurate load forecasting for a specific region would allow for more efficient management, planning, and scheduling of low-cost generation units and ensuring on-time energy delivery for full monetary benefit. Machine learning methods are becoming more effective on power grids as data availability increases. Ensemble learning models are hybrid algorithms that combine various machine learning methods and intelligently incorporate them into a single predictive model to reduce uncertainty and bias. In this study, several ensemble methods were implemented and tested for short-term electric load forecasting. The suggested method is trained using the influential meteorological variables obtained through correlation analysis and the past load. We used real-time load data from Nagaland's load dispatch centre in India and meteorological parameters of the Nagaland region for data analysis. The synthetic minority over-sampling technique for regression (SMOTE-R) is also employed to avoid data imbalance issues. The experimental results show that the Bagging methods outperform other models with respect to mean squared error and mean absolute percentage error. [ABSTRACT FROM AUTHOR]

Electricity is an important and one of the most dominant energy sources used in the world. It governs a major share in the Indian as well as world economy. Thus, forecasting its consumption can be useful in better planning of its future production and supply. In the present study, electricity consumption in seven different sectors, namely industry, domestic, agriculture, commercial, traction and railways, others along with total electricity consumed is forecasted using regression analysis. The study uses four regression modelling approaches to forecast electricity consumption by sectors in India. These are linear, logarithmic, power and exponential regression models. The accuracy of the models is tested using R² (coefficient of determination) and MAPE (mean absolute percentage error) values. The model having the highest R² and lowest MAPE value is selected for better accuracy results. The result/forecast is then compared with the available data published by the Central Electricity Authority, Government of India. [ABSTRACT FROM AUTHOR]

"Smart cities" start with "Smart Buildings" that improve the quality of urban services while ensuring sustainability. The current scenario in India reveals that the corporate and residential building structures are incorporating various self-sustainable techniques. Out of the multiple factors governing the comfort of smart buildings, indoor room temperature is an important one, since it drives the need of cooling or heating through controlling systems. Around one-third of total energy consumption of commercial buildings in India is attributed to Heating, Ventilation and Air Conditioning (HVAC) systems. Accurate prediction of indoor room temperature helps in creating an efficient equilibrium between energy consumption and comfort level of the building, thus providing opportunities for efficient decision making for energy optimization. Considering Indian climatic and geographical conditions, this paper proposes an efficient decision making approach using Bayesian Dynamic Models (BDM) for short-term indoor room temperature forecasting of a corporate building structure. The results obtained from Bayesian Dynamic linear model, using Expectation Maximization (EM) algorithm, have been compared to standard Auto Regressive Integrated Moving Average (ARIMA) model, and have been found to be more accurate. Forecasting of indoor room temperature is a highly nonlinear phenomenon, so to further improve the accuracy of the linear models, a hybrid modeling approach has been proposed. The inclusion of state-of-the-art nonlinear models such as Artificial Neural Networks (ANNs) and Support Vector Regression (SVR) improves the forecasting accuracy of the linear models significantly. Results show that the hybrid model obtained using BDM and ANN is the best fit model. [ABSTRACT FROM AUTHOR]

Forecasting of Indian summer monsoon rainfall (ISMR) is a complex problem for the hydrologists and meteorologists. The time series and data-driven methods have been used as complementary tools for forecasting ISMR against the complex physically based dynamical models due to scarcity of data and the simplicity of former approaches. The use of hybrid decomposition data–driven models is the recent improvement among the different approaches for rainfall forecasting, but these approaches differ significantly in the framework adopted. This paper presents an adaptive hybrid modelling framework so called Adaptive Ensemble Empirical Mode Decomposition-Artificial Neural Network (AEEMD-ANN) model for forecasting ISMR, which performs the forecasts adaptively as and when new information is added. The performance of the popular EEMD-ANN hybrid hindcast and forecast experiments in the prediction of All-India SMR and southwest monsoon rainfall of the state of Kerala is compared with the proposed method. The AEEMD-ANN method achieved a predictive skill of 0.78 and 0.91, respectively for rainfall predictions for Kerala and All-India. AEEMD-ANN method performed reasonably well in capturing the hydrologic extremes when compared with EEMD-ANN forecast method, with better accuracy in capturing the drought years. The proposed method is found to be successful in capturing the extreme low SWM rainfall of year 2002 for All-India and the extreme high rainfall of Kerala 2018 with an error percentage of 1.09% and 0.52%, respectively. [ABSTRACT FROM AUTHOR]

Accuracy of reservoir capacity loss estimation on daily timescale is dependent on the certainty of sediment load prediction, density estimate and capacity observed by consecutive hydrographic surveys. Data-scarce and uncertain data conditions restrict the development of a relationship between hydrographic surveys and hydrometric observations. The present study has been carried for Ukai Reservoir, India. A novel sediment rating curve fitting approach by optimization technique has been proposed in order to accurately predict sediment load from low-frequency sampled discharge and sediment concentration observations. The study demonstrates the validation of the bulk density estimate using statistical hypothesis testing and identifies the correctness of the hydrographic survey results. Application of the developed hydrometric and hydrographic relationship indicated that about 50% of the capacity loss of a year might occur during a single extreme event. The proposed approach can serve as a decision support system to monitor and manage sedimentation for the reservoir having uncertain data conditions. [ABSTRACT FROM AUTHOR]

This paper proposes a new hybrid season specific approach to incorporate the seasonality effect in short term load forecasting (STLF). A new season specific similarity concept (SSSC) is utilized to perceive the season specific meteorological necessities (seasonality effect) and integrates them in STLF process. The proposed approach is based on firefly algorithm (FA), support vector machine (SVM) and the new SSSC. The study is conducted in Assam, India and the proposed approach is designed to forecast load during different seasonal native meteorological conditions. Four case studies in four different seasons of a calendar year are carried out. The consideration of seasonality effect is found essential for a precise STLF under diverse seasonal meteorological conditions. This is because the electric load is influenced by different meteorological variables depending on different seasons. The numerical application of the proposed approach demonstrates higher forecasting accuracy in comparison to traditional approach of integrating temperature into STLF without considering any seasonality effect. To uphold the efficacy of the proposed approach, forecasting results are also compared with another traditional approach of integrating multiple meteorological variables into STLF without any seasonal considerations. Hence, the robustness of proposed approach is approved by its superior forecasting ability in all cases. • Offers a season specific approach for short term load forecasting in the study area. • Evaluation of season specific effective meteorological variables on load demand. • Proposes new season specific similarity concept to integrate the seasonality effect. • Integration of ineffective meteorological variable misguide the forecasting process. • The results affirm the superiority of the proposed approach in load forecasting. [ABSTRACT FROM AUTHOR]

Day-ahead load forecasting plays a crucial role in operation and management of power systems. Weather conditions have a significant impact on daily load profile, hence, it follows an almost similar pattern within a season. However, it varies markedly across the seasons. Existing literature on load forecasting adopts a very casual approach in considering the seasonality, based on either calendar month or some meteorological parameter, which is inconsistent and inaccurate, especially during transition periods, thus leading to high forecasting errors. This paper proposes a novel seasonal segmentation approach for day-ahead load forecasting that uses multiple bidirectional Long Short Term Memory (LSTM) networks. An index has been derived from various weather parameters that govern the selection of seasonal models for forecasting purposes. Weighted output from multiple seasonal models is also possible in special cases for better forecasting accuracy. The proposed seasonal segmentation approach avoids the need for frequent model retraining and results in a better forecast accuracy with a relatively simple LSTM structure. The performance of the proposed method has been validated and compared on the actual load data of Madhya Pradesh state (MP), India. The improved results suggest that the proposed approach can be applied reliably for load scheduling applications. • An encoder-decoder Bi-LSTM model with attention is developed to train the models. • An adaptive method for accurate identification of seasonal duration is proposed. • An index based selective and weighted method is developed for optimized forecasts. • Dynamic Time Warping (DTW) is used to adaptively select the forecast models. [ABSTRACT FROM AUTHOR]

Microplastic particles are found in environmental compartments all over the world and receive a great deal of attention, especially in the aquatic environment. Currently, a particularly high input of microplastics via Asian rivers is assumed, but so far, there are hardly any data through field measurements. Three rivers in South India were considered for this purpose to focus on their microplastic load. The emphasis was on the comparison of microplastic concentrations in urban and rural rivers. While two rivers in the megacity Chennai (Tamil Nadu) were found to have an average microplastic concentration of 0.4 microplastic particles/L, a rural river near Munnar (Kerala) had an average concentration of 0.2 microplastic particles/L. Rough estimates of annual microplastic discharge from the Adyar River (Chennai) into the Bay of Bengal are found to be as high as 11.6 trillion microplastic particles. This study should be one of the first baseline studies for microplastic loads in South Indian streams and should be complemented with further environmental sampling before, during and after the monsoon season to get more detailed information on the storage and transportation of fluvial microplastics under different weather conditions. [ABSTRACT FROM AUTHOR]

• Offers a new method of short term load forecasting for regional special event days. • Integrate social considerations like rituals (consumer behaviors) in forecasting. • Proposes a new concept of similarity to integrate consumer behaviors in forecasting. • Grey wolf optimizer is introduced to evaluate the parameters of SVM. • The results affirm the superiority of the proposed method in load forecasting. This paper offers a novel method of power system load forecasting (PSLF) for regional special event days (RSEDs) when the load demand is highly prejudiced by societal considerations like cultural or religious rituals. These rituals abruptly change the consumer behaviors (demand variations) and it makes the load profile of such RSEDs more complex and nonlinear than normal holidays. Therefore, during RSEDs, an accurate PSLF method must integrate these consumer behaviors in the forecasting process. For this purpose, the offered method uses a new concept of similarity. The offered method is based on support vector machine (SVM) hybridized with a new algorithm called grey wolf optimizer (GWO) to access the proper parameter combinations of SVM for PSLF on RSEDs. This research is carried out in Assam and the novel method is designed to forecast electric power load demand in three RSEDs called Rongali Bihu, Durga Puja, and Diwali. The forecasting results of the offered method demonstrate superior accuracy while compared to the traditional method of training the PSLF system on the data of recent holidays. The efficacy of the offered method is upheld by comparing the forecasting performances with four different standard and recent methods namely, SVM, ANN, PSO-SVM and GA-SVM. [ABSTRACT FROM AUTHOR]

With the increasing population and rising living standard, the demand for energy and materials have increased to a greater extent. The accurate estimation of increasing electricity demand is prerequisite for strategies planning, improving revenue, reducing power wastage and stable operation of the energy demand management system. Recent advancements in the field of electricity load forecasting provide powerful tools to capture non-linear energy demand trends and outperform conventional load prediction models. However, the existing demand prediction models suffer from some significant shortcomings that need to be addressed for improved prediction accuracy. In this context, the current research work proposes a deep learning based hybrid approach which firstly implements Variational Mode Decomposition (VMD) and Autoencoder models to extract meaningful sub-signals/features from the data. Subsequently, a Long Short-term Memory (LSTM) network model is trained for each sub-signal to forecast electricity demand by utilizing historical, seasonal and timestamp data dependencies. The support for incorporating seasonal and timestamp information to LSTM model is provided through the agglomerative clustering algorithm. Furthermore, an error variance modelling strategy is also employed to enhance the prediction accuracy of the proposed approach. The experiments are conducted on electricity consumption dataset of Himachal Pradesh, India. Performance assessment of the proposed approach is made by comparing prediction results with Support Vector Regression (SVR), Recurrent Neural Network (RNN), Deep Belief Network (DBN) and EMD+LSTM models. The experimental results demonstrate that the proposed model outperforms other state-of-the-art demand forecasting models and has the lowest MAPE (3.04%). • A decomposition-based multilevel systematic hybrid approach is proposed for load forecasting. • The decomposition algorithm in integration with autoencoder and LSTM model provides support for both improved accuracy and reduced complexity. • An error-variance modelling strategy is employed for the improved generalized performance. • The proposed approach outperforms other state-of-the-art prediction models and has the lowest MAPE (3.04%). [ABSTRACT FROM AUTHOR]

In this research, two hybrid intelligent models are proposed for prediction accuracy enhancement for wind speed and power modeling. The established models are based on the hybridisation of Ensemble Empirical Mode Decomposition (EEMD) with a Pattern Sequence-based Forecasting (PSF) model and the integration of EEMD-PSF with Autoregressive Integrated Moving Average (ARIMA) model. In both models (i.e., EEMD-PSF and EEMD-PSF-ARIMA), the EEMD method is used to decompose the time-series into a set of sub-series and the forecasting of each sub-series is initiated by respective prediction models. In the EEMD-PSF model, all sub-series are predicted using the PSF model, whereas in the EEMD-PSF-ARIMA model, the sub-series with high and low frequencies are predicted using PSF and ARIMA, respectively. The selection of the PSF or ARIMA models for the prediction process is dependent on the time-series characteristics of the decomposed series obtained with the EEMD method. The proposed models are examined for predicting wind speed and wind power time-series at Maharashtra state, India. In case of short-term wind power time-series prediction, both proposed methods have shown at least 18.03 and 14.78 percentage improvement in forecast accuracy in terms of root mean square error (RMSE) as compared to contemporary methods considered in this study for direct and iterated strategies, respectively. Similarly, for wind speed data, those improvement observed to be 20.00 and 23.80 percentages, respectively. These attained prediction results evidenced the potential of the proposed models for the wind speed and wind power forecasting. The current proposed methodology is transformed into R package 'decomposedPSF' which is discussed in the Appendix. [ABSTRACT FROM AUTHOR]