A growing number of households benefit from government subsidies to install renewable generation facilities such as PV panels, used to gain independence from the grid and provide cheap energy. In the Romanian electricity market, these prosumers can sell their generation surplus only at regulated prices, back to the grid. A way to increase the number of prosumers is to allow them to make higher profit by selling this surplus back into the local network. This would also be an advantage for the consumers, who could pay less for electricity exempt from network tariffs and benefit from lower prices resulting from the competition between prosumers. One way of enabling this type of trade is to use peer-to-peer contracts traded in local markets, run at microgrid (μG) level. This paper presents a new trading platform based on smart peer-to-peer (P2P) contracts for prosumers energy surplus trading in a real local microgrid. Several trading scenarios are proposed, which give the possibility to perform trading based on participants’ locations, instantaneous active power demand, maximum daily energy demand, and the principle of first come first served implemented in an anonymous blockchain trading ledger. The developed scheme is tested on a low-voltage (LV) microgrid model to check its feasibility of deployment in a real network. A comparative analysis between the proposed scenarios, regarding traded quatities and financial benefits is performed.

In this paper, we used the single-photon emission computerized tomography (SPECT) imaging technique to visualize the deficiency of dopamine-generated patterns inside the brain. These patterns are used to establish a patient’s disease progression, which helps distinguish the patients into different categories. Furthermore, we used a convolutional neural network (CNN) model to classify the patients based on the dopamine level inside the brain. The dataset used throughout this paper is the Parkinson’s progressive markers initiative (PPMI) dataset. The collected dataset was pre-processed and data amplification was performed to balance the imbalanced dataset. A CNN-based neural network was defined to classify input SPECT images into four categories. The motivation behind the proposed model is to reduce the number of resources consumed while maintaining the performance of the classification model. This will help the healthcare ecosystem run the classification model on mobile devices. The proposed model contains 14 layers with input layers, convolutional layers, max-pool layers, flatten layers, and dense layers with different dimensions. The dense layer classifies the patients into four different categories, including PSD, healthy control, scans without evidence of dopaminergic deficit (SWEDD), and GenReg PSD from the entire SPECT imaging dataset, which is used to establish the disease progression of different patients using SPECT images. The proposed model is trained with a large dataset with 58,692 images for training and 11,738 images for validation, and 7826 for testing. The proposed model outperforms the classification models from the surveyed papers. The proposed model’s accuracy is 0.889, recall is 0.9012, the precision is 0.9104, and the F1-score is 0.9057.

The global climate change mitigation efforts have increased the efforts of national governments to incentivize local households in adopting PV panels for local electricity generation. Since PV generation is available during the daytime, at off-peak hours, the optimal management of such installations often considers local storage that can defer the use of local generation to a later time. The energy stored in batteries located in optimal places in the network can be used by the utility to improve the operation conditions in the network. This paper proposes a metaheuristic approach based on a genetic algorithm that considers three different scenarios of using energy storage for reducing the energy losses in the network. Two cases considers the battery placement and operation under the direct control of the network operator, with single and multiple bus and phase placement locations. Here, the aim was to maximize the benefit for the whole network. The third case considers selfish prosumer battery management, where the storage owner uses the batteries only for their own benefit. The optimal design of the genetic algorithm and of the solution encoding allows for a comparative study of the results, highlighting the important strengths and weaknesses of each scenario. A case study is performed in a real distribution system.

Energy losses and bus voltage levels are key parameters in the operation of electricity distribution networks (EDN), in traditional operating conditions or in modern microgrids with renewable and distributed generation sources. Smart grids are set to bring hardware and software tools to improve the operation of electrical networks, using state-of the art demand management at home or system level and advanced network reconfiguration tools. However, for economic reasons, many network operators will still have to resort to low-cost management solutions, such as bus reactive power compensation using optimally placed capacitor banks. This paper approaches the problem of power and energy loss minimization by optimal allocation of capacitor banks (CB) in medium voltage (MV) EDN buses. A comparison is made between five metaheuristic algorithms used for this purpose: the well-established Genetic Algorithm (GA); Particle Swarm Optimization (PSO); and three newer metaheuristics, the Bat Optimization Algorithm (BOA), the Whale Optimization Algorithm (WOA) and the Sperm-Whale Algorithm (SWA). The algorithms are tested on the IEEE 33-bus system and on a real 215-bus EDN from Romania. The newest SWA algorithm gives the best results, for both test systems.

Energy efficiency is a major concern for utilities. For electricity transmission and distribution companies, while efficiency can be achieved by replacing old equipment from the networks with newer devices, or incorporating into the existing infrastructure additional components, such as FACTS solutions, all these measures are costly and require major changes in the network, with added time and financial costs. These measures should be applied only after all other options, which do not incur additional costs, are exhausted. One of these measures is Phase Load Balancing (PLB). This paper proposes a PLB approach built using the Particle Swarm optimization (PSO) algorithm. The PSO-PLB algorithm is tested on a real low voltage (LV) electricity distribution network (EDN), and the results, measured in electricity savings though loss reduction, prove its efficiency.

The pressure of climate change and the need to adopt renewable energy sources (RES) have led to an increased development of microgrid technologies. Their modularizable and scalable nature presents opportunities for the development of a new class of players in the power system, i.e. prosumers. The large-scale integration of RES creates acute challenges to the existing power systems. In this context, a reliable and secured balance between energy generation and consumption is highly required. To overcome these problems at microgrid level, a key role is played by the peer-to-peer energy trading using the blockchain concept. In this paper, we present an efficient approach that can be useful for energy trading using blockchain from both active participants (prosumers and consumers). The proposed approach meets the new Romanian regulation regarding prosumers. The results of the study emphasize that the proposed methodology could lead to an efficient balance between local supply and demand with benefits to the participants.