The stochastic nature of renewable energy sources, especially solar PV output, has created uncertainties for the power sector. It threatens the stability of the power system and results in an inability to match power consumption and production. This paper presents a Convolutional Neural Network (CNN) approach consisting of different architectures, such as the regular CNN, multi-headed CNN, and CNN-LSTM (CNN-Long Short-Term Memory), which utilizes a sliding window data-level approach and other data pre-processing techniques to make accurate forecasts. The output of the solar panels is linked to input parameters such as irradiation, module temperature, ambient temperature, and windspeed. The benchmarking and accuracy metrics are calculated for 1 h, 1 day, and 1 week for the CNN based methods which are then compared with the results from the autoregressive moving average and multiple linear regression models in order to demonstrate its efficacy in making short-term and medium-term forecasts.

The massive installation of renewable energy sources together with energy storage in the power grid can lead to fluctuating energy consumption when there is a bi-directional power flow due to the surplus of electricity generation. To ensure the security and reliability of the power grid, high-quality bi-directional power flow prediction is required. However, predicting bi-directional power flow remains a challenge due to the ever-changing characteristics of power flow and the influence of weather on renewable power generation. To overcome these challenges, we present two of the most popular hybrid deep learning (HDL) models based on a combination of a convolutional neural network (CNN) and long-term memory (LSTM) to predict the power flow in the investigated network cluster. In our approach, the models CNN-LSTM and LSTM-CNN were trained with two different datasets in terms of size and included parameters. The aim was to see whether the size of the dataset and the additional weather data can affect the performance of the proposed model to predict power flow. The result shows that both proposed models can achieve a small error under certain conditions. While the size and parameters of the dataset can affect the training time and accuracy of the HDL model.

This paper presents an energy management system for the microgrid present at Wroclaw University of Science and Technology. It has three components: a forecasting system, an optimizer and an optimized electrical vehicle charging station as a separate load for the system. The forecasting system is based on a deep learning model utilizing a Long Short-Term Memory (LSTM) – Autoencoder based architecture. The study provides a statistical analysis of its performance over several runs and addresses reliability and running time issues thereby building a case for its adoption. A MIDACO – MATPOWER combined optimization algorithm has been used as the optimization algorithm for energy management which intends to harness the speed of MATPOWER and the search capabilities of Mixed Integer Distributed Ant Colony Optimization (MIDACO) in finding an appropriate global minimum solution. The objective of the system is to minimize the import of power from the main grid resulting in improved self-sufficiency. Finally, an optimized electrical vehicle charging station model to maximize the renewable energy utilization within the facility is incorporated into the same.

The article presents calculations and power flow of a real virtual power plant (VPP), containing a fragment of low and medium voltage distribution network. The VPP contains a hydropower plant (HPP), a photovoltaic system (PV) and energy storage system (ESS). The purpose of this article is to summarize the requirements for connection of generating units to the grid. Paper discusses the impact of the requirements on the maximum installed capacity of distributed energy resource (DER) systems and on the parameters of the energy storage unit. Firstly, a comprehensive review of VPP definitions, aims, as well as the characteristics of the investigated case study of the VPP project is presented. Then, requirements related to the regulation, protection and integration of DER and ESS with power systems are discussed. Finally, investigations related to influence of DER and ESS on power network condition are presented. One of the outcomes of the paper is the method of identifying the maximum power capacity of DER and ESS in accordance with technical network requirements. The applied method uses analytic calculations, as well as simulations using Matlab environment, combined with real measurement data. The obtained results allow the influence of the operating conditions of particular DER and ESS on power flow and voltage condition to be identified, the maximum power capacity of ESS intended for the planed VPP to be determined, as well as the influence of power control strategies implemented in a PV power plant on resources available for the planning and control of a VPP to be specified. Technical limitations of the DER and ESS are used as input conditions for the economic simulations presented in the accompanying paper, which is focused on investigations of economic efficiency.

This paper analyzes the technical and economic possibilities of integrating distributed energy resources (DERs) and energy-storage systems (ESSs) into a virtual power plant (VPP) and operating them as a single power plant. The purpose of the study is to assess the economic efficiency of the VPP model, which is influenced by several factors such as energy price and energy production. Ten scenarios for the VPP were prepared on the basis of the installed capacities of a hydropower plant (HPP), rooftop solar photovoltaic (PV), and energy-storage system (ESS), as well as weather conditions, in Poland. On the basis of technical conditions, it was assumed that the maximum power capacity of the ESS equaled 1.5 MW. The economic efficiency analysis presented in this paper demonstrated that, in seven years, the VPP will achieve a positive value of the net present value (NPV) for a scenario with 0.5 MW battery storage and rainy summers. Furthermore, sensitivity analysis was conducted on price factors and DER production volume. The price variable had a major impact on the NPV value for all scenarios. The scenario with a 0.5 MW battery and typical summers was highly sensitive to all factors, and its sensitivity decreased as the ESS capacity grew from 0.5 to 1.5 MW.