Search

This document is a guest editorial from the journal IET Generation, Transmission & Distribution. It discusses the use of artificial intelligence (AI) in reliable forecasting for energy sectors. The editorial highlights the challenges of integrating renewable energy sources and fluctuating electricity demand, and emphasizes the importance of accurate forecasting for system operators. The document also provides summaries of several papers included in a special issue on AI-empowered forecasting in energy sectors, covering topics such as load forecasting, wind power prediction, and control parameter optimization. The editorial concludes by recommending further research and practical implementations of AI approaches in the energy sectors. [Extracted from the article]

Renewable energy sources have recently been integrated into microgrids that are in turn connected to electric vehicle (EV) charging stations. In this regard, the optimal planning of microgrids is challenging with such uncertain generation and stochastic charging/discharging EV models. To achieve such ambitious goals, the best sites and sizes of photovoltaic and wind energy units in microgrids with EV are accurately determined in this work using an optimization technique. This proposed technique considers 1) generation profile uncertainty in photovoltaic and wind energy units as well as the total load demand, 2) photovoltaic and wind generation units' DSTATCOM operation capability, and 3) various branch and node constraints in the microgrid. Most importantly, the possible EV requirements are also taken into account, including initial and predetermined state of charge (SOC) arrangements, arrival and departure hours, and diverse regulated and unregulated charging strategies. A bi‐level metaheuristic‐based solution is established to address this complex planning model. The outer level and inner‐level functions optimize renewable energy sources and EV decision variables. Sub‐objectives to be optimized voltage deviations as well as grid power. The results demonstrate the effectiveness of the introduced method for planning renewable energy sources and managing EV to effectively achieve autonomous microgrids. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) is one of the most promising renewable energy sources. To ensure secure operation and economic integration of PV in smart grids, accurate forecasting of PV power is an important issue. In this paper, we propose the use of long short-term memory recurrent neural network (LSTM-RNN) to accurately forecast the output power of PV systems. The LSTM networks can model the temporal changes in PV output power because of their recurrent architecture and memory units. The proposed method is evaluated using hourly datasets of different sites for a year. We compare the proposed method with three PV forecasting methods. The use of LSTM offers a further reduction in the forecasting error compared with the other methods. The proposed forecasting method can be a helpful tool for planning and controlling smart grids. [ABSTRACT FROM AUTHOR]

For the past few years, the world has seen a great shift toward renewable energy resources from conventional ones. But the ever‐increasing integration of distributed generation (DG) to the electrical network leads to integration limiting constraints like overvoltage, under voltage, harmonics, equipment ampacity violations, and failure of protection schemes. Therefore, an extensive investigation of the methodologies in which DGs can be incorporated into the electrical network is presented in this manuscript. This article provides an extensive review of all the hosting capacity (HC) terms, references, limiting constraints of the studied networks, geographical segregation, and their determination methodologies. Moreover, the factors defining the HCs of various networks and the architectures employed to increase them, are also explained briefly in the conducted review study. [ABSTRACT FROM AUTHOR]

Distribution system planners and operators have increasingly exposed great attention to maximizing the penetration of renewable energy resources (RERs), and electric vehicles (EVs) toward modern microgrids. Accordingly, intensive operational and economic problems are expected in such microgrids. Specifically, the operators need to meet the increased demand for EVs and increase the dependence on RERs. The charging strategy for EVs and the RER penetration level may result in increased power loss, thermal loading, voltage deviation, and overall system cost. To address these concerns, this paper proposed an optimal planning approach for allocating EV charging stations with controllable charging and hybrid RERs within multi‐microgrids, where the charging strategy in the proposed planning approach contributed to improving power quality and overall system cost, where the voltage deviation, energy not supplied, total cost have been reduced to 26.03%, 49.57%, and 70.45%, respectively. The simulation results are compared with different optimization techniques to verify the effectiveness of the proposed algorithm. The proposed simultaneous allocation approach of EV charging stations and RERs can reduce operating costs for RERs and conventional stations while increasing the charging stations' capacity. [ABSTRACT FROM AUTHOR]

• A novel approach is proposed for maximizing photovoltaic hosting capacity. • The reactive power sources and transformer taps are considered. • The stochastic nature of electric vehicles is considered. • A double-layer metaheuristic optimizer is developed. • IEEE 69-bus distribution system is used for simulation. The interest in maximizing the hosting capacity of photovoltaics is recently being enlarged globally. This paper proposes a novel stochastic approach for maximizing the hosting capacity of photovoltaics in distribution systems. The proposed approach is based on a coordinated management scheme of control devices in distribution systems, i.e. transformer taps and VAr sources. It also considers the promising electrical vehicles with their stochastic nature and comprehensive model, including the arriving and departing times, and initial and preset conditions of their batteries state of charge. Further, the planning model of photovoltaics considers the reactive power support of the photovoltaic inverter based on the recently released IEEE 1547:2018 standard. Compared to existing approaches, the unique merit of the proposed approach is its ability to maximize the hosting capacity of photovoltaics by simultaneous optimization of the different control variables. To accurately solve this stochastic optimization model, a double-layer metaheuristic optimizer is developed for maximizing the hosting capacity of photovoltaics and addressing all constraints. The inner level of the optimizer optimizes the charging/discharging power of electric vehicles, transformer taps, and reactive power support while the outer one maximizes the sizes of photovoltaics. To assess the effectiveness of the proposed approach, various scenarios are performed on the IEEE 69-bus distribution system. The proposed approach can maximize the hosting capacity of photovoltaics while optimally managing transformers, VAr sources, and electric vehicles in a coordinated manner. [ABSTRACT FROM AUTHOR]

For the past few years, the addition of renewable energy sources has been on the rise, but the unregulated addition of these sources can cause severe harm to the grid. Therefore, it is necessary to have a predefined limit for a grid, beyond which no further addition of renewables should be allowed without reinforcement. That limit is called the hosting capacity (HC), which is addressed in the literature by search‐based methods with heavy computational burdens. This manuscript first presents a framework to find the HC for a grid. The same framework is then applied to 503 different simulated but realistic LV distribution feeders in Finland to find their HCs and the most effective network parameters in defining a network specific HC. Next, different machine learning models, that is, Decision Tree (DT), Random Forest (RF), Linear Regression (LR), K nearest neighbours (KNN), Logistic Regression, and Support Vector Machine (SVM) are implemented on the generated data. For the classification case, the accuracy values for logistic regression, KNN, and SVM were 0.89, 0.84, and 0.81, respectively. The findings demonstrate that the developed machine learning based technique will enable distribution network operators in finding the HC without applying any deterministic or probabilistic approaches. [ABSTRACT FROM AUTHOR]

The rapid increase in the installation of renewable energy sources, particularly solar photovoltaic (PV) sources associated with unbalanced features of distribution systems (DS), disturbs the classic control strategy of voltage regulation devices and causes voltage violation problems. This paper proposes an effective control strategy for voltage regulators in the DS based on the voltage sensitivity using a multi-agent system (MAS) architecture. The features of the unbalanced distribution system (UDS) with the PV and different types and configurations of voltage regulators are considered in the proposed strategy. The novelty of the proposed method lies in realizing both the control optimality of minimizing voltage violations and the flexibility to accommodate changes in the DS topology using an MAS scheme. An advantageous feature of using the MAS scheme is the robust control performance in normal operation and against system failure. Simulation studies have been conducted using IEEE 34-node and 123-node distribution test feeders considering high PV penetration and different sun profiles. The results show that the proposed voltage control strategy can optimally and effectively manage the voltage regulators in the UDS, which decrease their operation stresses and minimize the overall voltage deviation. [ABSTRACT FROM AUTHOR]

Achieving the goal of sustainable development is dependent on the widespread integration of renewable energy sources, energy storage systems (ESSs), and electric vehicles (EVs). However, a continuous increase in the penetration of such elements would bring more complexities to the distribution network. Accordingly, this paper presents a unified planning model comprising renewable energy-based distributed generation (DG), ESS, and electric vehicle charging stations (EVCSs). In this regard, a Latin Hypercube Sampling method is utilized to generate multi-scenario for describing the uncertainty of renewable energy and load demand. The stochastic EV charging behaviors are represented by various probability density functions (PDF). In addition, an exploitable capacity loss of ESS and EV batteries is calculated by the battery degradation model based on the depth of discharge (DOD). Furthermore, the battery degradation cost is incorporated into the objective of the planning model to identify the optimal decision for candidate assets. A piecewise linearization approach is introduced to convert the problem into a mix-integer linear programming (MILP) model. Numerical results demonstrate that the exploitable capacity loss of batteries plays a key role in asset planning and provides potential contributions to the optimal decisions of the distribution network. In the meantime, by considering battery degradation in the optimization model, the sustainability and lifetime of the battery can be preserved. • Uncertainties include the renewable energy, load demand, and behaviors of electric vehicles are considered. • Renewable energy-based DG, ESS, and EVCS are involved in the unified planning model. • The degradation model is proposed to analyze the exploitable capacity loss of ESS and EV battery. • The enhancement of investment decision while maintaining the lifetime of battery is achieved. [ABSTRACT FROM AUTHOR]

Highlights • A method is proposed to calculate the optimal oversize of the DG inverters. • The reactive power capability and active power curtailment are considered. • Different control schemes of the inverter are considered in the proposed method. • The effect of OLTC operation on the total costs and inverter oversize is studied. • IEEE 69-bus and IEEE 33-bus distribution systems are used for simulation. Abstract The penetration of renewable distributed generations (DG) is recently being increased in distribution systems. Due to the intermittent nature of these generation units, several technical problems are expected based on the environmental conditions and load profiles, such as voltage rise and increasing losses. A traditional way to alleviate these technical problems is to oversize their interfacing inverters for releasing their capacities to inject/absorb further reactive power. In the literature, the DG inverter is normally oversized by a certain percentage (e.g., 10%) for this purpose. In turn, an optimization-based method is proposed in this paper to calculate the optimal oversize of the interfaced inverter employed in various utility-owned DG types to regulate voltages and to reduce losses with minimum total costs. The proposed method considers the active power curtailment (APC) feature in the DG inverter and the transformer taps. Different control schemes of the interfaced inverter are considered and incorporated in the proposed optimization model. The simulation results demonstrate the effectiveness of the proposed method compared with existing methods. [ABSTRACT FROM AUTHOR]

The penetration of renewable energy sources (RES) has been increased throughout the world. The main characteristic of RESs is that their generating powers are intermittent and unpredictable. This paper presents an interval optimization method to optimally schedule electric vehicles (EV) with considering the uncertainty of RES generation and loads. For this purpose, the RES generation (including photovoltaic and wind power) and loads are considered as interval parameters, and the charging/discharging power of EV is expressed as an interval variable to be optimally computed. The capability of RES inverters to regulate voltages is also considered in the interval optimization model. The objective function is to minimize the network active power losses and total voltage magnitude deviation with considering overall system constraints. The proposed method is tested on a 33-bus distribution system with uncertain RESs and loads, and the optimal day-ahead scheduling of EV is performed. Different case studies are carried out to test the effectiveness of the proposed method. It is demonstrated that the proposed interval optimization method can accurately represent the uncertain problem, and it provides further information compared with the deterministic optimization. [ABSTRACT FROM AUTHOR]

Renewables (i.e., solar and wind power) in the Nordic area have highly seasonal characteristics, which severely restrict the wide development of renewables since they can be excessive in summer but insufficient in winter with intermittent outputs. The conventional battery energy storage system (BESS) with short-term adjustment functionality cannot eliminate the seasonal imbalance of renewables. In this regard, a risk-based bi-level planning model is presented to maximize the hosting capacity (HC) of renewables through configuring seasonal hydrogen storage (SHS) and BESS. Specifically, the upper level applies a multi-objective scheme to maximize HC and minimize the investment cost simultaneously. In turn, the lower level is driven by maximizing the profits of the distribution system operator (DSO) with the implementation of price-based demand response (PBDR). Due to forecasting errors of renewables and load resulting from intermittent output and random behaviors, a stochastic programming (SP) method is developed to address and adapt multiple uncertain fluctuations. Moreover, the conditional value-at-risk (CVaR) is introduced to measure the effect of the risks raised by multiple uncertainties on system operation. Finally, numerical studies are employed to verify the effectiveness of the proposed model. Compared to the cases without considering PBDR and SHS, the total renewable energy HC in the proposed model is increased by 2.30 MW and 0.37 MW, respectively, while the yearly cost benefit of DSO is enhanced by 28063.2 US$ and 17823.7 US$, respectively. The promising results demonstrate the empowerment of SHS can promote the cross-seasonal consumption of renewables, effectively maximizing the HC and improving the economic operation of distribution systems. • The hydrogen storage system is considered in this work for the cross-seasonal balance of renewables. • A bi-level planning model is proposed to improve hosting capacity and economic operation of the system. • The coordinated operation of seasonal hydrogen storage, demand response, and battery storage is designed. • The uncertainties and the operation risk brought by renewables and load are considered. [ABSTRACT FROM AUTHOR]

Currently, distribution systems are continuously evolving towards modern and flexible structures while integrating promising renewable energy resources (RERs). In this regard, an optimal network constraint-based expansion planning model combined with an optimal integration framework of intermittent RERs is proposed in this work to improve the topological flexibility in modern distribution networks (DNs). Specifically, the best investment locations and times of substations, lines, and RER-based distributed generations (DGs) are jointly taken into consideration. Additionally, the uncertainty-based multiple scenarios are modeled by probability distribution functions to strengthen the robustness and reliability of DNs influenced by the stochastic of renewable energy and load behavior. The novel network constraint is combined with three levels, where the first level introduces the graph theory to guarantee the radiality topology of modern DNs. In the second level of the network constraint, graph theory and fictitious load theory are collaboratively applied to ensure that each subsystem has a reserve connection interconnected to other subsystems. The third level is modifying the conventional fictitious load theory to ensure each subsystem is linked with at least one DG. The proposed planning model is driven by the minimum present value of total cost, including investment cost of branches, DGs, and substations, cost of substations operation, the electricity purchasing cost of substations and DGs, power losses cost, and environmental penalty cost of conventional generators. Numerical results are presented to verify that a more flexible and resilient topology of the DN system is obtained, and criteria evaluation is introduced to validate its higher performance with respect to existing procedures from power supplied quality, environmental burden, and supplied flexibility three aspects. [ABSTRACT FROM AUTHOR]

• A novel probabilistic approach for evaluating DERs hosting capacity utilizing large number of feeders. • Monte Carlo simulations are conducted to model the intermittency associated with the DERs' integration in the distribution networks. • Impact of different network factors like node distance, customer count, impedance, and feeder length on hosting capacity are analysed. • Provides a practical lookup table for aiding distribution network operators (DNOs) during feeder planning. Increasing the adoption of renewable energy, especially photovoltaics (PVs), can have a positive impact on the environment and economies. However, the unplanned inclusion of these renewable resources into the grid system can give rise to serious constraint violations (voltage violations, over-currents, overloading of transformers) for the distribution system. In this regard, the primary intention of this study is to firstly identify the type of constraints that may be violated, and then quantify the hosting capacity (HC) for a particular feeder. Monte Carlo simulations were used to counter the uncertainties and variability related to loading behaviour and the randomness in the location and size of PV. The study was conducted on 507 realistic and distinct Finnish low-voltage distribution systems. The occurrence of the limiting constraints on HC and the pattern of their occurrence is explained. In the end, a correlation analysis is also performed using some key parameters of the grid to highlight the factors which influence the HC value the most. [ABSTRACT FROM AUTHOR]

• Optimization-based method is proposed for voltage fluctuations smoothing due to RES. • The reactive power capability of RES inverters is considered. • The fluctuations of EV powers and their minimum SOC at departure time are considered. • Hull moving average (HMA) is used to mitigate voltage fluctuations. • IEEE 90-bus and IEEE 33-bus distribution systems are used for simulation. Recently, the use of renewable energy sources (RES) and electric vehicles (EVs) has been rapidly increased worldwide. As a result of the highly fluctuating nature of RES, the charging and discharging rates of EVs significantly have to be increased, and so the lifespan of EV batteries decreases. In this paper, an optimization-based method is proposed to smooth voltage fluctuations due to various RES types by optimally controlling the charging and discharging power of EVs and the reactive power of the RES inverters. To extend the lifespan of the EV battery, EV power fluctuations and their minimum preset state of charge (SOC) are considered in the proposed optimization model. For this purpose, a new multi-objective function is formulated, including (1) voltage fluctuations, (2) EV power fluctuations, and (3) the deviation of SOC of EVs from their minimum desired level. The use of the hull moving average (HMA) is proposed to mitigate voltage fluctuations, which eliminates the lag problem of the widely used moving average methods. The gravitational search algorithm (GSA) is utilized to accurately solve the optimization model. The simulation results demonstrate the effectiveness of the proposed method to smooth voltage fluctuations while considering degradation and charging plan of EV batteries. [ABSTRACT FROM AUTHOR]