Search

Accurate and interpretable short-term load forecasting tasks are essential to the optimal operation of liberalized electricity markets since they contribute to the efficient development of energy trading and demand response strategies as well as the successful integration of renewable energy sources. Consequently, performant day-ahead consumption forecasting models need to capture feature nonlinearities, analyze system dynamics and conserve evolving temporal patterns in order to minimize the impact of noise and adapt to concept drift. Prominent estimators and standalone decomposition-based approaches may not fully address those challenges as they often yield small error rate improvements and omit optimal time series evolution. Therefore, in this work we propose a combinatorial component decomposition method focused on the selection of important renewable generation component sequences extracted from the combined output of seasonal-trend decomposition using locally estimated scatterplot smoothing, singular spectrum analysis and empirical mode decomposition methods. The proposed method was applied on five well-known kernel models in order to evaluate day-ahead consumption forecasts on linear, tree-based and neural network structures. Moreover, for the assessment of pattern conservation, an intuitive metric function, labeled as Weighted Average Unanchored Chain Divergence (WAUCD), based on distance scores and unanchored time series chains is introduced. The results indicated that the application of the combinatorial component method improved the accuracy and the pattern conservation capabilities of most models substantially. In this examination, the long short-term memory (LSTM) and deep neural network (DNN) kernels reduced their mean absolute percentage error by 46.87% and 42.76% respectively and predicted sequences that consistently evolved over 30% closer to the original target in terms of daily and weekly patterns. [ABSTRACT FROM AUTHOR]

The electricity market is constantly evolving, being driven by factors such as market liberalization, the increasing use of renewable energy sources (RESs), and various economic and political influences. These dynamics make it challenging to predict wholesale electricity prices. Accurate short-term forecasting is crucial to maintaining system balance and addressing anomalies such as negative prices and deviations from predictions. This paper investigates short-term electricity price forecasting using historical time series data and employs advanced deep learning algorithms. First, four deep learning models are implemented and proposed, which are a convolutional neural network (CNN) with an integrated attention mechanism, a hybrid CNN followed by a gated recurrent unit model (CNN-GRU) with an attention mechanism, and two ensemble learning models, which are a soft voting ensemble and a stacking ensemble model. Also, the optimized version of a transformer model, the Multi-Head Attention model, is introduced. Finally, the perceptron model is used as a benchmark for comparison. Our results show excellent prediction accuracy, particularly in the hybrid CNN-GRU model with attention, thereby achieving a mean absolute percentage error (MAPE) of 6.333%. The soft voting ensemble model and the Multi-Head Attention model also performed well, with MAPEs of 6.125% and 6.889%, respectively. These findings are significant, as previous studies have not shown high performance with transformer models and attention mechanisms. The presented results offer promising insights for future research in this field. [ABSTRACT FROM AUTHOR]

In this paper, a stochastic multi-objective intelligent framework (MOIF) is performed for distribution network reconfiguration to minimize power losses, the number of voltage sags, the system's average RMS fluctuation, the average system interruption frequency (ASIFI), the momentary average interruption frequency (MAIFI), and the system average interruption frequency (SAIFI) considering the network uncertainty. The unscented transformation (UT) approach is applied to model the demand uncertainty due to its being simple to implement and requiring no assumptions to simplify it. A human-inspired intelligent method named improved mountaineering team-based optimization (IMTBO) is used to find the decision variables defined as the network's optimal configuration. The conventional MTBO is improved using a quasi-opposition-based learning strategy to overcome premature convergence and achieve the optimal solution. The simulation results showed that in single- and double-objective optimization some objectives are weakened compared to their base value, while the results of the MOIF indicate a fair compromise between different objectives, and all objectives are enhanced. The results of the MOIF based on the IMTBO clearly showed that the losses are reduced by 30.94%, the voltage sag numbers and average RMS fluctuation are reduced by 33.68% and 33.65%, and also ASIFI, MAIFI, and SAIFI are improved by 6.80%, 44.61%, and 0.73%, respectively. Also, the superior capability of the MOIF based on the IMTBO is confirmed compared to the conventional MTBO, particle swarm optimization, and the artificial electric field algorithm. Moreover, the results of the stochastic MOIF based on the UT showed the power loss increased by 7.62%, voltage sag and SARFI increased by 5.39% and 5.31%, and ASIFI, MAIFI, and SAIFI weakened by 2.28%, 6.61%, and 1.48%, respectively, compared to the deterministic MOIF model. [ABSTRACT FROM AUTHOR]

There is a technological necessity for more efficient, abundant, and sustainable materials for energy storage applications. Lithium-ion batteries dominate, however, there are a number of sustainability, economic, and availability issues that require the investigation of post-lithium batteries. In essence, the drive is to move to non-lithium-containing batteries as there is simply not enough lithium available to satisfy demand in a few years. To find alternative ions migrating at appropriate rates in crystal lattices requires significant research efforts and, in that respect, computational modeling can accelerate progress. The review considers recent mainly theoretical results highlighting the kinetics of ions in post-lithium oxides. It is proposed that there is a need for chemistries and ionic species that are sustainable and abundant and in that respect sodium, magnesium, and oxygen ion conduction in batteries is preferable to lithium. The limitations and promise of these systems are discussed in view of applications. [ABSTRACT FROM AUTHOR]

In recent years, the interest in electric vehicles (EVs) in the research community has been growing, particularly in the context of decarbonization. Additionally, there is a growing increase in their number, leading to massive energy demand on the charging stations (CSs). Energy trading management for CSs puts great pressure on the power grid and is a stimulating challenge in smart cities. In this paper, we propose an innovative market formulation in which autonomous vehicles and smart charging and discharging stations are motivated to cooperate dynamically with changing roles. In order to mathematically formulate the energy trading market, we adopt a double auction strategy that is repeated in steps. In this strategy, EVs and CSs participate by buying and selling energy. The investigated problem has high complexity, and thus, multi-objective optimization is employed so as to encapsulate the opposing objectives that the EVs and CSs have. Multi-objective optimization leads to a fairer and more efficient market operation. The performance of the presented approach is investigated through analytical and experimental results. More specifically, the proposed algorithm achieves up to 52.5 % reduction in energy consumption. The performance evaluation proves that the suggested strategy offers both fairness and significant energy benefits, encouraging both electric vehicles and charging stations to take part in a double auction energy trading system. [ABSTRACT FROM AUTHOR]

In recent times, the power sector has become a focal point of extensive scientific interest, driven by a convergence of factors, such as mounting global concerns surrounding climate change, the persistent increase in electricity prices within the wholesale energy market, and the surge in investments catalyzed by technological advancements across diverse sectors. These evolving challenges have necessitated the emergence of new imperatives aimed at effectively managing energy resources, ensuring grid stability, bolstering reliability, and making informed decisions. One area that has garnered particular attention is the accurate prediction of end-user electricity load, which has emerged as a critical facet in the pursuit of efficient energy management. To tackle this challenge, machine and deep learning models have emerged as popular and promising approaches, owing to their having remarkable effectiveness in handling complex time series data. In this paper, the development of an algorithmic model that leverages an automated process to provide highly accurate predictions of electricity load, specifically tailored for the island of Thira in Greece, is introduced. Through the implementation of an automated application, an array of deep learning forecasting models were meticulously crafted, encompassing the Multilayer Perceptron, Long Short-Term Memory (LSTM), One Dimensional Convolutional Neural Network (CNN-1D), hybrid CNN–LSTM, Temporal Convolutional Network (TCN), and an innovative hybrid model called the Convolutional LSTM Encoder–Decoder. Through evaluation of prediction accuracy, satisfactory performance across all the models considered was observed, with the proposed hybrid model showcasing the highest level of accuracy. These findings underscore the profound significance of employing deep learning techniques for precise forecasting of electricity demand, thereby offering valuable insights with which to tackle the multifaceted challenges encountered within the power sector. By adopting advanced forecasting methodologies, the electricity sector moves towards greater efficiency, resilience and sustainability. [ABSTRACT FROM AUTHOR]

The advent of the point-contact transistor is one of the most significant technological achievements in human history with a profound impact on human civilization during the past 75 years. Although the first transistor was made of germanium it was soon replaced by silicon, a material with lower intrinsic carrier mobilities but with a substantially better native oxide. Interestingly, more than two decades ago, germanium was once again considered as a mainstream microelectronic material, since the introduction of high-k dielectrics allowed the consideration of channel materials irrespective of the quality of their native oxide. After about 50 years of limited studies on the defect processes in germanium, the community once again focused on its applicability for mainstream electronic applications. Nevertheless, there are some bottlenecks that need to be overcome, and it was the aim of the present review to discuss the progress in the understanding of the defect processes of Ge. [ABSTRACT FROM AUTHOR]

Accurate electricity demand forecasting is vital to the development and evolution of smart grids as well as the reinforcement of demand side management strategies in the energy sector. Since this forecasting task requires the efficient processing of load profiles extracted from smart meters for large sets of clients, the challenges of high dimensionality often lead to the adoption of cluster-based aggregation strategies, resulting in scalable estimation models that operate on aggregate times series formed by client groups that share similar load characteristics. However, it is evident that the clustered time series exhibit different patterns that may not be processed efficiently by a single estimator or a fixed hybrid structure. Therefore, ensemble learning methods could provide an additional layer of model fusion, enabling the resulting estimator to adapt to the input series and yield better performance. In this work, we propose an adaptive ensemble member selection approach for stacking and voting regressors in the cluster-based aggregate forecasting framework that focuses on the examination of forecasting performance on peak and non-peak observations for the development of structurally flexible estimators for each cluster. The resulting ensemble models yield better overall performance when compared to the standalone estimators and our experiments indicate that member selection strategies focusing on the influence of non-peak performance lead to more performant ensemble models in this framework. [ABSTRACT FROM AUTHOR]

Network infrastructure sharing and mobile traffic offloading are promising technologies for Heterogeneous Networks (HetNets) to provide energy and cost effective services. In order to decrease the energy requirements and the capital and operational expenditures, Mobile Network Operators (MNOs) and third parties cooperate dynamically with changing roles leading to a novel market model, where innovative challenges are introduced. In this paper, a novel resource sharing and offloading algorithm is introduced based on a double auction mechanism where MNOs and third parties buy and sell capacity and roam their traffic among each other. For low traffic periods, Base Stations (BSs) and Small Cells (SCs) can even be switched off in order to gain even more in energy and cost. Due to the complexity of the scenario, we adopt the multi-objective optimization theory to capture the conflicting interests of the participating entities and we design an iterative double auction algorithm that ensures the efficient operation of the market. Additionally, the selection of the appropriate time periods to apply the proposed algorithm is of great importance. Thus, we propose a machine learning technique for traffic load prediction and for the selection of the most effective time periods to offload traffic and switch off the Base Stations. Analytical and experimental results are presented to assess the performance of the algorithm. [ABSTRACT FROM AUTHOR]

The technological requirement for ever more efficient materials for the energy and electronics sectors has led to the consideration of numerous compositionally and structurally complicated systems. These systems include solid solutions that are difficult to model using electronic structure calculations because of the numerous possibilities in the arrangement of atoms in supercells. The plethora of such possible arrangements leads to extensive and large numbers of potential supercells, and this renders the investigation of defect properties practically intractable. We consider recent advances in oxide interfaces where studies have demonstrated that it is feasible to tune their defect processes effectively. In this review, we aim to contribute to the ongoing discussion in the community on simple, efficient and tractable ways to realise research in solid solutions and oxide interfaces. The review considers the foundations of relevant thermodynamic models to extract point defect parameters and the special quasirandom structures method to model the supercell of solid solutions. Examples of previous work are given to highlight these methodologies. The review concludes with future directions, systems to be considered and a brief assessment of the relevant methodologies. [ABSTRACT FROM AUTHOR]

In this paper we address dynamic assumption-based reasoning in open agent systems, where, unavoidably, agents have incomplete knowledge about their environment and about other agents. The interactions among agents in such systems are typically subject to norms, which stipulate what each agent is obliged, permitted, prohibited, empowered etc. to do, while it participates in the system. In such environments agents need to resort to assumptions, in order to establish what actions are appropriate to perform, and they need to do so dynamically, since the environment, the agents that exist in it, the information that is exchanged between them, and the normative relations between them change over time. In earlier work, we had proposed Default Theory construction to support dynamic assumption-based reasoning. We argued that in this way, agents could perform both assumption identification and employment dynamically, contrary to other approaches to assumption-based reasoning, which catered for either one or the other. A shortcoming of this early proposal of ours, though, is that Default Theory construction seems to require proof, which is notably computationally expensive. In this paper we present a computational technique that can be used for this construction in an incremental manner that does not depend on proof, and a prototype tool that we developed for experimentation. In a nutshell, depending on their current knowledge at any given time, agents can identify appropriate candidate assumptions in an ad hoc manner. When such choices need to be revised, agents can reconstruct their view of the possible world in which they find themselves, and establish their revised assumption requirements at run-time. [ABSTRACT FROM AUTHOR]

The evolution of electricity markets has led to increasingly complex energy trading dynamics and the integration of renewable energy sources as well as the influence of several external market factors contributed towards price volatility. Therefore, day-ahead electricity price forecasting models, typically using some kind of neural network, play a crucial role in the optimal behavior of market agents. The most prominent models and benchmarks rely on improving the accuracy of predictions and the time for convergence by some sort of a priori processing of the dataset that is used for the training of the neural network, such as hyperparameter tuning and feature selection techniques. What has been overlooked so far is the possible benefit of a posteriori processing, which would consider the effects of parameters that could refine the predictions once they have been made. Such a parameter is the estimation of the residual training error. In this study, we investigate the effect of residual training error estimation for the day-ahead price forecasting task and propose an error compensation deep neural network model (ERC–DNN) that focuses on the minimization of prediction error, while reinforcing error stability through the integration of an autoregression module. The experiments on the Nord Pool power market indicated that this approach yields improved error metrics when compared to the baseline deep learning structure in different training scenarios, and the refined predictions for each hourly sequence shared a more stable error profile. The proposed method contributes towards the development of more flexible hybrid neural network models and the potential integration of the error estimation module in future benchmarks, given a small and interpretable set of hyperparameters. [ABSTRACT FROM AUTHOR]

The stable and efficient operation of power systems requires them to be optimized, which, given the growing availability of load data, relies on load forecasting methods. Fast and highly accurate Short-Term Load Forecasting (STLF) is critical for the daily operation of power plants, and state-of-the-art approaches for it involve hybrid models that deploy regressive deep learning algorithms, such as neural networks, in conjunction with clustering techniques for the pre-processing of load data before they are fed to the neural network. This paper develops and evaluates four robust STLF models based on Multi-Layer Perceptrons (MLPs) coupled with the K-Means and Fuzzy C-Means clustering algorithms. The first set of two models cluster the data before feeding it to the MLPs, and are directly comparable to similar existing approaches, yielding, however, better forecasting accuracy. They also serve as a common reference point for the evaluation of the second set of two models, which further enhance the input to the MLP by informing it explicitly with clustering information, which is a novel feature. All four models are designed, tested and evaluated using data from the Greek power system, although their development is generic and they could, in principle, be applied to any power system. The results obtained by the four models are compared to those of other STLF methods, using objective metrics, and the accuracy obtained, as well as convergence time, is in most cases improved. [ABSTRACT FROM AUTHOR]

The growing demand for electricity runs counter to European-level goals, which include activities aimed at sustainable development and environmental protection. In this context, efficient consumption of electricity attracts much research interest nowadays. One environment friendly solution to meet increased demand lies in the deployment of Renewable Energy Sources (RES) in the network and in mobilizing the active participation of consumers in reducing the peak of demand, thus smoothing the overall load curve. This paper addresses the issue of efficient and economical use of electricity from the Demand Side Management (DSM) perspective and presents an implementation of a fully-parameterized and explicitly constrained incentive-based demand response program The program uses the Particle Swarm Optimization algorithm and demonstrates the potential advantages of integrating RES while supporting two-way communication between energy production and consumption and two-way power exchange between the main grid and the RES. [ABSTRACT FROM AUTHOR]

In this paper we describe an implementation of the on-line validation algorithm for the analysis of occluded images, which was developed by Iliopoulos and Simpson [Iliopolous, C.S. and Simpson, J. (1997)]. The algorithm operates on images represented in one dimension as strings and assumes objects within images are of the same length. We also investigate the decomposition of a given image into the set of (perhaps partially occluded) objects occurring in it. We first present the theoretical background to this work and sketch the main components of the analysis and validation method. Then we discuss implementation issues and the testing techniques used and present the test results. [ABSTRACT FROM AUTHOR]

Power forecasting models offer valuable insights on the electricity consumption patterns of clients, enabling the development of advanced strategies and applications aimed at energy saving, increased energy efficiency, and smart energy pricing. The data collection process for client consumption models is not always ideal and the resulting datasets often lead to compromises in the implementation of forecasting models, as well as suboptimal performance, due to several challenges. Therefore, combinations of elements that highlight relationships between clients need to be investigated in order to achieve more accurate consumption predictions. In this study, we exploited the combined effects of client similarity and causality, and developed a power consumption forecasting model that utilizes ensembles of long short-term memory (LSTM) networks. Our novel approach enables the derivation of different representations of the predicted consumption based on feature sets influenced by similarity and causality metrics. The resulting representations were used to train a meta-model, based on a multi-layer perceptron (MLP), in order to combine the results of the LSTM ensembles optimally. This combinatorial approach achieved better overall performance and yielded lower mean absolute percentage error when compared to the standalone LSTM ensembles that do not include similarity and causality. Additional experiments indicated that the combination of similarity and causality resulted in more performant models when compared to implementations utilizing only one element on the same model structure. [ABSTRACT FROM AUTHOR]

Hybrid Renewable Energy Systems (HRES) are an attractive solution for the supply of electricity in remote areas like islands and communities where grid extension is difficult. Hybrid systems combine renewable energy sources with conventional units and battery storage in order to provide energy in an off-grid or on-grid system. The purpose of this study is to examine the techno-economical feasibility and viability of a hybrid system in Donoussa island, Greece, in different scenarios. A techno-economic analysis was conducted for a hybrid renewable energy system in three scenarios with different percentages of adoption rate (20%, 50% and 100%)and with different system configurations. Using HOMER Pro software the optimal system configuration between the feasible configurations of each scenario was selected, based on lowest Net Present Cost (NPC), minimum Excess Electricity percentage, and Levelized Cost of Energy (LCoE). The results obtained by the simulation could offer some operational references for a practical hybrid system in Donoussa island. The simulation results confirm the application of a hybrid system with 0% of Excess Electricity, reasonable NPC and LCoE and a decent amount of renewable integration. [ABSTRACT FROM AUTHOR]

Modern energy automation solutions and demand response applications rely on load profiles to monitor and manage electricity consumption effectively. The introduction of smart control systems capable of handling additional fuzzy parameters, such as weather data, through machine learning methods, offers valuable insights in an attempt to adjust consumer behavior optimally. Following recent advances in the field of fuzzy control, this study presents the design and implementation of a fuzzy control system that processes environmental data in order to recommend minimum energy consumption values for a residential building. This system follows the forward chaining Mamdani approach and uses decision tree linearization for rule generation. Additionally, a hybrid feature selector is implemented based on XGBoost and decision tree metrics for feature importance. The proposed structure discovers and generates a small set of fuzzy rules that highlights the energy consumption behavior of the building based on time-series data of past operation. The response of the fuzzy system based on sample input data is presented, and the evaluation of its performance shows that the rule base generation is derived with improved accuracy. In addition, an overall smaller set of rules is generated, and the computation is faster compared to the baseline decision tree configuration. [ABSTRACT FROM AUTHOR]

Power forecasting is an integral part of the Demand Response design philosophy for power systems, enabling utility companies to understand the electricity consumption patterns of their customers and adjust price signals accordingly, in order to handle load demand more effectively. Since there is an increasing interest in real-time automation and more flexible Demand Response programs that monitor changes in the residential load profiles and reflect them according to changes in energy pricing schemes, high granularity time series forecasting is at the forefront of energy and artificial intelligence research, aimed at developing machine learning models that can produce accurate time series predictions. In this study we compared the baseline performance and structure of different types of neural networks on residential energy data by formulating a suitable supervised learning problem, based on real world data. After training and testing long short-term memory (LSTM) network variants, a convolutional neural network (CNN), and a multi-layer perceptron (MLP), we observed that the latter performed better on the given problem, yielding the lowest mean absolute error and achieving the fastest training time. [ABSTRACT FROM AUTHOR]