Smart Grid Energy Management System for Industrial Applications

This paper presents the development of a conceptual map regarding energy management applied to industry. The energy issue is currently of great relevance, especially for the so-called energy-intensive industries related to high energy consumption and their associated environmental impacts. The present research is characterized as a basic, exploratory approach justified by the need to build knowledge on the subject of energy management in industry. The methodology provides for the use of a computational tool called CMap Tools, which assists in the graphic representation of the proposed conceptual map. The conceptual map based on the ISO 50001 standard and on successful energy management practices described in the scientific literature is directed toward a process design covered by the managerial discipline called Business Process Management. The conceptual map is intended to clarify the relationships that are established between the intra-organizational and main external stakeholders involved in an energy management system. Owing to the way internal areas and external organizations relate, the representation structure using a “Spider” is the most appropriate. The work developed presents an energy management system for an energy-intensive industry in a clear (conceptually and visually), orderly, unified, harmonious, and balanced manner indicating the distribution of its elements, and serves as an initial step in the creation of an ontology for this area of knowledge.

Prediction concept needs human-like thinking and ideas. ANN helps make a program for describing the solutions to the prediction problems. To gain accurate prediction, there is a need for deep thinking in the knowledge system discovered. Deep learning helps form such next-level type of ANN thinking. Deep learning models do not require humans for programming the problems. It can determine the prediction by itself by learning the dataset. This paper describes the prediction by considering sequential model for continuous accessing of data with the help of multi-layers. Deep learning is very helpful for predicting larger dataset. This paper proposes an algorithmic model known as a Comprehensive Deep Recurrent Artificial Neural Networks (CDRANN) by hybridizing LSTM (long short-term memory) with RNN (recurrent neural network) backtrack solver for better future stock prediction. This paper also explains the need for hybridizing evolutionary model CDRANN to create a novel change in future prediction.KeywordsCDRANN (Comprehensive Deep Recurrent Artificial Neural Networks)LSTM (long short-term memory)RNN (recurrent neural network)Stock marketPrediction

In this work, we introduce load prediction as continuous input for optimization models within an optimization framework for short-term control of complex energy systems. In this context, we investigated long short-term memory (LSTM) models for load prediction, because they allow incremental training in an application with continuous real-time data and have not been used in other works for continuous load prediction to our knowledge. The test and evaluation were realized using data sets of real residential data from different locations in different time resolution - hourly and minutely. Accordingly, we tested different recurrent neural network (RNN) parameters of the model such as the number of layers, the number of hidden nodes, the inclusion of regularization, and dropout in order to find the optimal LSTM configuration for our continuous load prediction application. Besides, we analyzed the quality of the LSTM algorithm by comparing it in continuous mode with the baseline model and in batch mode with the statistical model ARIMA. Training and prediction time, as well as the error stabilization time were parameters used for the evaluation. The results showed that LSTM algorithms are highly promising for integrating continuous load prediction with incremental learning.

Integration of demand side and supply side energy management resources for optimal scheduling of demand response loads – South Africa in focus

Recurrent Neural Networks (RNNs), which are a powerful scheme for modeling temporal and sequential data need to capture long-term dependencies on datasets and represent them in hidden layers with a powerful model to capture more information from inputs. For modeling long-term dependencies in a dataset, the gating mechanism concept can help RNNs remember and forget previous information. Representing the hidden layers of an RNN with more expressive operations (i.e., tensor products) helps it learn a more complex relationship between the current input and the previous hidden layer information. These ideas can generally improve RNN performances. In this paper, we proposed a novel RNN architecture that combine the concepts of gating mechanism and the tensor product into a single model. By combining these two concepts into a single RNN, our proposed models learn long-term dependencies by modeling with gating units and obtain more expressive and direct interaction between input and hidden layers using a tensor product on 3-dimensional array (tensor) weight parameters. We use Long Short Term Memory (LSTM) RNN and Gated Recurrent Unit (GRU) RNN and combine them with a tensor product inside their formulations. Our proposed RNNs, which are called a Long-Short Term Memory Recurrent Neural Tensor Network (LSTMRNTN) and Gated Recurrent Unit Recurrent Neural Tensor Network (GRURNTN), are made by combining the LSTM and GRU RNN models with the tensor product. We conducted experiments with our proposed models on word-level and character-level language modeling tasks and revealed that our proposed models significantly improved their performance compared to our baseline models.

This article proposes an energy management system (EMS) for a fuel cell (FC) hybrid electric vehicle. The EMS is based on nonlinear model predictive control (NMPC) and employs a recurrent neural network (RNN) for modeling a proton exchange membrane FC. The NMPC makes possible the formulation of control objectives not allowed by a linear model predictive control (MPC), such as maximum efficiency point tracking of the FC, while the RNN can accurately predict the FC nonlinear dynamics. The EMS was implemented on a low-cost development board, and the experiments were performed in real time on a hardware-in-the-loop test bench equipped with a real 3-kW FC stack. The experimental results demonstrate that the NMPC EMS is able to meet the vehicle's energy demand, as well as to operate the FC in its most efficient region. Moreover, a comparative study is performed between the proposed NMPC, a linear MPC, and hysteresis band control. The results of this comparative study demonstrate that the NMPC provides a better fuel economy and can reduce FC degradation.

This paper introduces a hybrid algorithm that combines machine learning and modified teaching learning-based optimization (TLBO) for enhancing smart city communication and energy management. The primary objective is to optimize the modified systems, which face challenges due to their high population density. The proposed algorithm integrates the strengths of machine learning techniques, more specifically, the long short-term memory (LSTM) technique, with teaching learning-based optimization algorithms. To achieve optimization, the algorithm learns from historical data on energy consumption and communication patterns specific to the modeled system. By leveraging these insights, it can predict future energy consumption and communication patterns accurately. Additionally, the algorithm incorporates a modified teaching learning-based optimization approach inspired by the teaching and learning process in classrooms. It adjusts the system parameters based on feedback received from the system, thereby optimizing both energy consumption and communication systems. The effectiveness of the proposed algorithm is evaluated through a case study conducted on the test system, where historical data on energy consumption and communication patterns are analyzed. The results demonstrate that the algorithm efficiently optimizes the communication and energy management systems, leading to substantial energy savings and improved communication efficiency within the test system. In conclusion, this study presents a hybrid machine learning and modified teaching learning-based optimization algorithm that effectively addresses the communication and energy management challenges in the test system. Moreover, this algorithm holds the potential for application in various smart city domains beyond the test system. The findings of this research contribute to the advancement of smart city technologies and offer valuable insights into reducing energy consumption in densely populated urban areas.

Recurring wildfires pose a critical global issue as they undermine social and economic stability and jeopardize human lives. To effectively manage disasters and bolster community resilience, the development of wildfire susceptibility maps (WFSMs) has emerged as a crucial undertaking in recent years. In this research endeavor, two deep learning algorithms were leveraged to generate WFSMs using two distinct remote sensing datasets. Specifically, the Moderate-Resolution Imaging Spectroradiometer (MODIS) and Landsat-8 images were utilized to monitor wildfires that transpired during the year 2021. To develop an effective WFSM, two datasets were created by incorporating 599 wildfire locations with Landsat-8 images and 232 sites with MODIS images, as well as twelve factors influencing wildfires. Deep learning algorithms, namely the long short-term memory (LSTM) and recurrent neural network (RNN), were utilized to model wildfire susceptibility using the two datasets. Subsequently, four WFSMs were generated using the LSTM (MODIS), LSTM (Landsat-8), RNN (MODIS), and RNN (Landsat-8) algorithms. The evaluation of the WFSMs was performed using the area under the receiver operating characteristic (ROC) curve (AUC) index. The results revealed that the RNN (MODIS) (AUC = 0.971), RNN (Landsat-8) (AUC = 0.966), LSTM (MODIS) (AUC = 0.964), and LSTM (Landsat-8) (AUC = 0.941) algorithms demonstrated the highest modeling accuracy, respectively. Moreover, the Gini index was employed to assess the impact of the twelve factors on wildfires in the study area. The results of the random forest (RF) algorithm indicated that temperature, wind speed, slope, and topographic wetness index (TWI) parameters had a significant effect on wildfires in the study region. These findings are instrumental in facilitating efficient wildfire management and enhancing community resilience against the detrimental effects of wildfires.

Worldwide, the current energy system increasingly shows economic, social and environmental drawbacks and it does not appear to be sustainable. Among the most pressing problems are climate change due to CO2 emissions, the depletion of fossil resources, the security of energy supply, and threats to economic development. These problems can be addressed by moving towards energy systems that increasingly rely on renewable and sustainable energy sources. At the same time, the rapid progress in renewable energy harvesting and information and telecommunication technologies offer unprecedented opportunities for energy generation, distribution and management, and to more strongly involve people in the process of energy generation and management, which is needed to further enhance the sustainable energy systems. Indeed, renewable and sustainable energy sources are likely to be produced and distributed in a decentralised manner, and require energy management systems that differ greatly from the current centralised system. Hence, the integration of renewable sources has major implications for the design and management of energy systems, relying on innovative ICT solutions and stronger user involvement that facilitate supply and demand matching. Effective energy management requires the active participation and support of end users, who should accept the energy management systems, and adapt their energy use to the available demand as to enhance the efficiency and stability of the energy system. Hence, the design of future smart grids should be based on sound behavioural models, which should be integrated in ICT centred solutions that facilitate supply and demand matching. More specifically, we need to understand how truly complex information on energy production, use and storage can be effectively communicated among relevant actors, and what type of information and incentives should be provided to realise effective supply and demand matching. In addition, we need to understand how to take into account cultural specifics in the design of energy management systems, to enhance effective energy management across the world. The active and aware involvement of the end-user can only be achieved if a scalable and reliable ICT infrastructure is in place, which naturally interfaces the energy flows with the decision autonomy of the people. Hence, the design of effective energy management systems should be take into account key behavioural as well as ICT requirements in an integrated way. Our proposal is thus to investigate (1) ICT based solutions for monitoring and controlling the power grid focusing on the distribution networks (medium-low voltage) and buildings (offices and residential complexes) specific to the Qatar context; (2) behavioural models on effective and acceptable incentives to match energy supply and demand; (3) cultural specificities in the design of energy management systems by comparing results from research in Qatar to similar research in other parts of the world, in particular Europe. Together, these will provide important insights in how to promote efficient and stable renewable energy systems that meet Qatar's sustainability goals.

This paper state the optimization of household and apartment energy management system. The content propose 4 parts: the introduction including the background and the theory of household and apartment energy management systems; the design of household energy management (HEM) optimization systems which include the hardware implementation and software application; some case studies are discussed to illustrate the optimization results are effective, for instance it shows clearly that bills are reduced after optimize process; the final conclusions are indicated in the end. The mathematical model was built to solve the optimization problem. The usage of appliances are automatically changed by the system depend on the day-ahead electrical price. The control algorithm is depend on the mixed integer linear programming (MILP). Power balance is the most core idea of the system, since the shared battery system is raised and played as an important role in the control strategy. 4 households are combined together by using one shared battery storage system, which promote the optimization results. There are four case studies are supposed in this paper, which reflected in the impact of different price mechanism; the impact of critical load; the impact of battery size and the impact of generation part. These case studies are comprehensive discussed to certify the optimization effect is obvious.

Photovoltaic power generation is one of the most efficient renewable energy generation techniques. To ensure photovoltaic (PV) safe operation and cost-effective integration into smart grids. As a result, a realistic PV power forecast method can aid in mitigating PV power generation’s drawbacks, which is critical for power plant maintenance and repair. In this research, we compared two Deep Learning models which are both highly advantageous, namely a long short-term memory (LSTM) and a recurrent neural network (RNN). A case study employing an actual dataset obtained from 1B DKASC, Alice Springs, Australia, is used to demonstrate the performance of LSTM and RNN. The forecasts generated by the LSTM are compared with the results of RNN using MAE, MSE, MBE, R\(^2\) and RMSE for all the forecast horizons. The results of the study demonstrate that the LSTM based forecast outperforms RNN and has the potential to improve the accuracy and stability of the prediction.KeywordsDeep LearningLong Short-Term Memory (LSTM)Recurrent neural network (RNN)

Recurrent neural networks (RNN) are at the core of modern automatic speech recognition (ASR) systems. In particular, long short-term memory (LSTM) recurrent neural networks have achieved state-of-the-art results in many speech recognition tasks, due to their efficient representation of long and short term dependencies in sequences of inter-dependent features. Nonetheless, internal dependencies within the element composing multidimensional features are weakly considered by traditional real-valued representations. We propose a novel quaternion long short-term memory (QL-STM) recurrent neural network that takes into account both the external relations between the features composing a sequence, and these internal latent structural dependencies with the quaternion algebra. QLSTMs are compared to LSTMs during a memory copy-task and a realistic application of speech recognition on the Wall Street Journal (WSJ) dataset. QLSTM reaches better performances during the two experiments with up to 2.8 times less learning parameters, leading to a more expressive representation of the information.

Abstract— Stocks are investments that have dynamic movements. Stock price changes move every day even hourly. With very fast changes, stock prices require predictions to be able to determine stock market projections. Predictions are used to reduce risk when making transactions. In this study, predictions of stock price trends were made using the Recurrent Neural Network (RNN). The approach taken is to perform a time series analysis using the RNN variance, namely Long Short Term Memory (LSTM). Hyperparameter construction in the LSTM model testing simulation can estimate stock prices with maximum percentage accuracy. The results showed that the prediction model produced a loss function of 0.0012 and a training time of 73 m/step. The evaluation was carried out with the RMSE which resulted in a score of 17.13325. Predictions are obtained after doing machine learning using 1239 data. The RMSE and LSTM models are calculated by changing the number of epochs, the variation between the predicted stock price and the current stock price. Computations are carried out using a stock market dataset that includes open, high, low, close, adj prices, closes, and volumes. The main objective of this study is to determine the extent to which the LSTM algorithm anticipates stock market prices with better accuracy. Code can be seen at iranihoeronis/RNN-LSTM (github.com) Keywords— Stock Prediction, Time Series, Recurrent Neural Network (RNN), Long Short Term Memory (LSTM).

One of the most promising tools in recent years for the analysis and prediction of time series data, which includes financial market data has been the use of neural networks. To ensure the accuracy of the outcomes of these systems, it is critical to overcome the vanishing gradient and exploding gradient problems that often occur when recurrent neural networks (RNN) process data. Long Short-Term Memory (LSTM) has been shown to provide good performance when dealing with time series datasets. This paper will explore the feasibility of using an RNN with LSTM as a predictive tool for use with futures trading data. Using a dataset comprised of all futures trading occurring on the Bourse de MontrA©al (TMX) during a 9-month period from January to September 2015, we assessed the predictive effectiveness of an RNN in predicting the price of front-end contracts for the futures symbol BAX. We found that while an RNN provided a degree of short-term predictive capability, this capability did not extend beyond a couple of days. Although it failed as a trading instrument to predict futures prices, the RNN could detect, identify, and reflect underlying trends in the data, indicating the tool may hold promise in the detection of trading patterns.Â

Efficient use of electric energy by users is one of the critical ways for increasing energy efficiency, reducing cost of power generation and supply, and environmental concerns. As part of remedial measures to address issues of energy use, many technologies for demand reduction ranging from energy saving devices through a variety of energy management systems have emerged to help users manage and control their consumption. In this paper, we present the design and implementation of a home energy and power management system that enables users to monitor, regulate, and manage their demand response dynamically through scheduling and controlling of their appliances using a mobile application. At the crux of the power management system is an embedded microcontroller which is encoded with schemes for monitoring, managing, scheduling and controlling operations. The user interface on the mobile device directly communicates with the power management system via integrated Raspberry Pi server that uses Wi-Fi communication protocol while communication between the Raspberry Pi and the embedded microcontroller is based on Bluetooth communication. A numerical simulation of the proposed design was first developed and a prototype of the design was implemented and tested. The test results show that the system was able to effectively monitor, control and regulate the power usage in the home. The flexibility offered by the system allows the user to self-regulate the amount of power usage, which translates into cost savings with the overall effect of flattening of the demand peaks.