•A new fuzzy clustering method classifies to more than one clusters an input vector in order to create ensemble predictions.•Radial basis function neural networks are trained using Adam algorithm as ...utilized in the Tensorflow network.•Convolutional neural networks are applied to analyze the RBF kernel activations.•An innovative neural network is proposed that consists of an RBF layer, a convolutional, a pooling layer and two fully connected layers.•The proposed model is evaluated to a national power system and to an isolated power system.
A novel, hybrid structure for week-ahead load forecasting is presented. It is the energy market evolution that compels its participants to require load predictions whose accuracy cannot be provided by traditional means. The proposed implementation combines attributes from ensemble forecasting, artificial neural networks and deep learning architectures. The proposed model initially clusters the input data using a novel fuzzy clustering method for creating an ensemble prediction. For each cluster created, a new regression approach is applied to model locally the load forecasting problem. Following a two-stage approach, initially, a radial basis function neural network (RBFNN) is trained using three-fold cross-validation and the hidden layers of the best three RBFNNs are used to transform the input data to a four dimensional dataset. Then, a convolutional neural network (CNN) is deployed receiving as input the latter dataset. Thus, a neural network is formed consisting of a radial basis function (RBF), a convolutional, a pooling and two fully-connected layers. Both RBFNNs and CNNs are trained with the Adam optimization algorithm within the Tensorflow deep learning framework. The proposed model is designed to predict the hourly load for the next seven days and its effectiveness is evaluated in two different case studies; namely the Hellenic interconnected power system and the isolated power system of Crete. Both case-studies exhibit the superior performance of the proposed model when compared to state-of-the-art and traditional load forecasting schemes.
The transformation of passive distribution systems to more active ones thanks to the increased penetration of distributed energy resources, such as dispersed generators, flexible demand, distributed ...storage, and electric vehicles, creates the necessity of an enhanced test system for distribution systems planning and operation studies. The value of the proposed test system, is that it provides an appropriate and comprehensive benchmark for future researches concerning distribution systems. The proposed test system is developed by modifying and updating the well-known 33 bus distribution system from Baran & Wu. It comprises both forms of balanced and unbalanced three-phase power systems, including new details on the integration of distributed and renewable generation units, reactive power compensation assets, reconfiguration infrastructures and appropriate datasets of load and renewable generation profiles for different case studies.
This paper proposes a new collaborative pricing scheme for a power-transportation coupled network based on the variational inequality (VI) approach. In the proposed scheme, nodal electricity prices ...and congestion tolls on roads and at charging stations are considered to coordinate the coupled networks in order to minimize the operational cost of the whole system. The prices are determined by a second-order cone-based AC power flow model and a mixed user equilibrium model, respectively. A collaborative pricing model (CPM) is then built based on the two models and the interactions between them. In order to avoid the intractability of the developed non-convex model, the CPM is transformed into the VI formulation. With proven existence and uniqueness of solutions of the VI formulation, a new prediction-correction algorithm is proposed to accelerate the solution of the CPM problem, which is guaranteed to converge to the optimal solution. The proposed models and algorithm are verified using case studies on a real-world test system. The results show that the proposed pricing scheme can reduce the operational cost and the proposed algorithm shows improved convergence and higher computation efficiency compared with the existing algorithms.
Power systems have typically been designed to be reliable to expected, low-impact high-frequency outages. In contrast, extreme events, driven for instance by extreme weather and natural disasters, ...happen with low-probability, but can have a high impact. The need for power systems, possibly the most critical infrastructures in the world, to become resilient to such events is becoming compelling. However, there is still little clarity as to this relatively new concept. On these premises, this paper provides an introduction to the fundamental concepts of power systems resilience and to the use of hardening and smart operational strategies to improve it. More specifically, first the resilience trapezoid is introduced as visual tool to reflect the behavior of a power system during a catastrophic event. Building on this, the key resilience features that a power system should boast are then defined, along with a discussion on different possible hardening and smart, operational resilience enhancement strategies. Further, the so-called ΦΛEΠ resilience assessment framework is presented, which includes a set of resilience metrics capable of modeling and quantifying the resilience performance of a power system subject to catastrophic events. A case study application with a 29-bus test version of the Great Britain transmission network is carried out to investigate the impacts of extreme windstorms. The effects of different hardening and smart resilience enhancement strategies are also explored, thus demonstrating the practicality of the different concepts presented.
As the amount of distributed generation (DG) is growing worldwide, the need to increase the hosting capacity of distribution systems without reinforcements is becoming nowadays a major concern. This ...paper explores how the DG hosting capacity of active distribution systems can be increased by means of network reconfiguration, both static, i.e., grid reconfiguration at planning stage, and dynamic, i.e., grid reconfiguration using remotely controlled switches as an active network management (ANM) scheme. The problem is formulated as a mixed-integer, nonlinear, multi-period optimal power flow (MP-OPF) which aims to maximize the DG hosting capacity under thermal and voltage constraints. This work further proposes an algorithm to break-down the large problem size when many periods have to be considered. The effectiveness of the approach and the significant benefits obtained by static and dynamic reconfiguration options in terms of DG hosting capacity are demonstrated using a modified benchmark distribution system.
•A complete review and categorization of NTL detection papers after 2010.•Categorization and definition of data sources and features used for NTL detection.•Definition and analysis of performance ...metrics used in NTL detection.•Overview of NTL detection algorithms and qualitative comparisons.•Presentation of most important NTL detection parameters per paper.
Electricity theft has been a major issue for many years. Distribution System Operators (DSOs) have been trying to detect electricity theft, however the phenomenon insists, while simple meter inspection methods cannot adequately identify most cases of fraud. In this paper the most recent and characteristic research papers on Non-Technical Loss (NTL) detection are reviewed and their key features are summarized. NTL detection schemes are organized in three large categories: data oriented, network oriented and hybrids. Data oriented and network oriented methods are further divided to subcategories, according to the main concept behind NTL detection. Apart from categorizing the various methods the authors focus on algorithms, data types and size, features, evaluation metrics and NTL detection system response times. An overview of the algorithms used by NTL detection systems is presented focusing on why they are suitable for the specific application. The data types consumed by each NTL detection system are defined and features typically extracted from these data types are presented. In addition, the authors provide a comprehensive list of performance metrics used and comment on their importance. Finally, a qualitative comparison of NTL detectors is provided focusing on performance issues, costs, data variety/quality issues and system response times.
The replacement of directly connected synchronous generators with power electronics interfaced generation has led to a decrease in system's inertia posing a significant challenge on frequency ...dynamics. In isolated systems with reduced inertia predefined limits for renewable penetration and primary reserves are frequently set for dynamic security purposes. This approach might not ensure dynamic security or can prove conservative in certain conditions. Furthermore, these approaches rarely consider the capabilities of inverter based renewable generation to provide frequency services. In this paper, a data driven approach, based on optimal classification trees is proposed to extract, from a detailed dynamic model of the system, the constraints for a frequency dynamic unit commitment formulation. Hence, both dynamic security and optimal exploitation of renewable and conventional units for power production and frequency support can be achieved. The advantages of the proposed method compared to conventional and state of the art approaches in frequency security are validated through dynamic simulations on a realistic model of Rhodes island and IEEE 118. Uncertainties in load demand and renewable generation are dealt by a robust optimization method. Its economic performance, computational overhead and modelling complexity is compared to a stochastic approach.
Several catastrophic experiences of extreme weather events show that boosting the power grid resilience is becoming increasingly critical. This paper discusses a unified resilience evaluation and ...operational enhancement approach, which includes a procedure for assessing the impact of severe weather on power systems and a novel risk-based defensive islanding algorithm. This adaptive islanding algorithm aims to mitigate the cascading effects that may occur during weather emergencies. This goes beyond the infrastructure-based measures that are traditionally used as a defense to severe weather. The resilience assessment procedure relies on the concept of fragility curves, which express the weather-dependent failure probabilities of the components. A severity risk index is used to determine the application of defensive islanding, which considers the current network topology and the branches that are at higher risk of tripping due to the weather event. This preventive measure boosts the system resilience by splitting the network into stable and self-adequate islands in order to isolate the components with higher failure probability, whose tripping would trigger cascading events. The proposed approach is illustrated using a simplified version of the Great Britain transmission network, with focus on assessing and improving its resilience to severe windstorms.
The aim of this paper is to propose a distributed electric vehicle (EV) coordination management which exploits the potentials of the bidirectional power flow between the grid and the EV. In the ...literature, the proposed distributed price-based EV coordination mechanisms aiming to achieve a valley-filling concept consider electric vehicles as mere manageable loads, which are served during valley hours given the EV energy requirements and mobility pattern. In this paper, a distributed EV coordination mechanism is proposed that utilizes 1) the flexibility of EV demand in order to efficiently allocate it during the valley period and hours with high distributed renewable energy production and 2) the vehicle-to-grid (V2G) EV capability in order to minimize the network load variance. The aim of the proposed EV coordination mechanism is to: 1) exploit the synergies between the renewable distributed energy resources (DER) and EV charging needs in order to increase the EV/RES penetration level of the grid without the need for further network investments and 2) exploit the bidirectional EV battery operation for more efficient network operation in terms of voltage profile and network losses. The proposed EV coordination mechanism is assessed through simulations of a realistic rural MV distribution network.