Search

This article proposes a hybrid method (HM) to improve the accuracy of short-term individual residential load forecasting. The HM includes an ensemble model (EM), deep ensemble model (DEM), and thermal dynamic model expressed by resistance-capacitance (RC). The EM consists of three predictors of support vector machine (SVM), back propagation neural network (BPNN), and generalized regression neural network (GRNN). The genetic algorithm (GA) is used to optimize SVM and BPNN to enhance their performance. The DEM includes multiple bi-directional long-short term memory (Bi-LSTM) networks. The Bayesian algorithm (BA) is used to optimize the hyperparameters of the Bi-LSTM. The outputs of individual predictors are aggregated using an optimal trimmed algorithm. At first, the total load is separated into the heater and air conditioning (HAC), and non-HAC loads. Then, the RC model is presented to predict the indoor temperature, which integrates outdoor weather and less HAC historical data as the input of the EM to forecast the HAC load. After that, non-HAC loads are further divided into electric lighting and other loads. A daylight equation is used to calculate the illuminance, which is combined with less lighting historical data as the input of DEM to predict electric lights usage. Then, other loads are captured by DEM through less historical data. Finally, the total load is obtained by combining the predicted HAC and non-HAC loads. The datasets from the UMass Smart Microgrid and Flexhouse projects are used to test the proposed method. The comparison with existing models proves that the presented model can provide accurate short-term individual load forecasting.

This article proposes a comprehensive multi-functional controller for a hybrid energy storage system (HESS), including a battery and supercapacitor (SC). In the presented method, a V-dP/dt is proposed to control the output power of the battery converter with a slow dynamic response. The traditional V-P droop is employed to regulate the SC converter to give a fast response. The dc bus voltage can be maintained in a safe range by the SC converter control so that no voltage recovery loop is required. Hence, the order of the overall control system and the complexity of parameter design can be reduced. In addition, a novel consensus-based voltage compensator is proposed to achieve the state of charge (SoC) balance and accurate power sharing among batteries. Then, an SoC restoration of the SC is used to address the leakage current and ensure sufficient energy for future use. Next, a power management scheme (PMS) is proposed to protect the batteries from over-use under different operating modes. Finally, the output impedance characteristics, control system design, and stability analysis are elaborated. The processor in the loop (PIL) simulation results verified the effectiveness and feasibility of the proposed control method.

•An alternative approach for determining rooftop area suitable for solar PV deployment using validated open source tools and a mathematical algorithm is proposed.•Possible solar PV generation and energy supply to the industry’s demand were evaluated.•An economic feasibility of the proposed solar PV system was evaluated.•Annual energy cost analysis due to implementation of solar PV system by the industry was evaluated.

•Control strategies for hybrid energy storage system in the microgrid are critical reviewed.•The impact of the communication delay on the centralized and distributed controls is studied.•A case study is used to provide a suggestive guideline for the design of the control system.

•Studied the optimal solar modules’ tilt angle in low latitude equatorial region.•Used Particle Swarm Optimization to maximize the annual solar irradiance received.•Found out the most suitable tilt angle to utilize is the annual optimal tilt angle.•Proposed a methodology for establishing the rooftop support structure adjustments.

Reports on the success of ComputerTown, USA! (CTUSA!), a computer literacy project funded by the United States National Science Foundation. Holding of computer-related activities at the Menlo Park Public Library in California; History; Goals of the project. INSET: World of Personal Computers..

•A store-on grid model for rooftop solar PV implementation is proposed.•Store-on grid fee and grid sellback rate methodologies were proposed.•Costs analysis under store-on grid scheme model for the Uganda’s industrial sector.•Energy costs under store-on grid model were compared with time of use rating model.•Prosumer registers annual energy cost reduction under store-on grid model.