Dynamic Load Demand Research Articles

Optimizing electric vehicle charging scheduling using enhanced multi-agent neural networks with dynamic pricing

Electric vehicles have gained widespread recognition as an environmentally conscious mode of transportation, primarily due to significant technological advancements and reduced emissions. When seamlessly integrated into the smart grid infrastructure, these vehicles can serve as flexible energy consumers and potential energy storage units. However, the efficient management of charging stations due to dynamic load demand & pricing poses a significant challenge, aiming to reduce wait times for electric vehicle owners and reduce electricity costs. To overcome this challenge, this study proposes a solution based on dynamic pricing policy and the adaptive Markov decision process. The approach utilizes a reinforcement learning-enabled enhanced multi-agent neural network (EMANN) to optimize charging schedules. This adaptive Markov decision process achieved optimal scheduling by minimizing charging costs during off-peak hours while completing charging in the shortest possible time. Furthermore, a constrained policy is employed to train the enhanced neural network using reinforcement learning, allowing the network to learn and solve adaptive Markov decision processes directly. To evaluate the effectiveness of this solution, the study conducted a numerical experiment using real-time data from Tesla electric vehicles. Combined with queuing models, the EMANN yielded impressive results, including a peak savings of 19.05% and an average profit of $376.1 per kilowatt-hour, achieved within a network convergence time of 512 s. The proposed algorithm for scheduling electric vehicles has been proven to be efficient in addressing the complexities associated with managing electric vehicle charging stations.

Study on dynamic mechanical properties and microstructure of basalt fiber reinforced coral sand cement composite *

This study investigates the impact of basalt fiber on the static and dynamic compression of coral-sand cement-based composites, as well as the mechanisms for strengthening and toughening. The samples of basalt fiber-reinforced coral sand cementitious composite (BFRCSCC) with varying fiber volume fractions (0%, 0.2%, 0.4%, 0.6%, 0.8%) underwent quasi-static mechanical tests and impact dynamic tests using an MTS universal testing machine and a split Hopkinson pressure bar (SHPB). This study investigates the mechanical properties of BFRCSCC, focusing on static and dynamic compressive strength, dynamic stress-strain curve, strain rate effect, failure strain, toughness analysis, and energy dissipation mechanism. In terms of microstructure, specimens of BFRCSCC were tested using scanning electron microscopy (SEM). The results indicate that basalt fiber can significantly enhance the quasi-static compressive strength (fc)and dynamic compressive strength (fd)of coral sand cement-based composite materials. When the basalt fiber content is 0.4%, the static and dynamic compressive strength of BFRCSCC increases by 28.78% and 37.25% respectively compared to ordinary concrete. The analysis from a micro perspective indicates that the incorporation of basalt fiber in the concrete matrix enhances the hydration reaction between cement and the BFRCSCC interface. The spatial structure formed by basalt fiber contributes to the excellent toughening effect on the mechanical properties of BFRCSCC. As the content of basalt fiber increases (≤0.4%), the bridging effect becomes stronger. The dynamic increase factor (DIF) and toughness index of BFRCSCC exhibit a significant positive correlation with the strain rate effect. Basalt fibers can help drive the hydration products to fill the cracks or voids in the cement matrix, thereby increasing the material's density and enhancing the impact resistance of coral concrete. This can be utilized in practical engineering projects with high dynamic load demands.

Solutions of economic load dispatch problems for hybrid power plants using Dandelion optimizer

In this paper, an economic load dispatch problem (ELD) is solved for reaching optimal power output of hybrid systems in addition to cost minimization. The systems consider the forbidden working zones (FWZs), dynamic load demand, wind farms, and solar photovoltaic fields (SPs). The cost minimization solutions for the ELD problem are found by applying the Dandelion optimizer (DO), the salp swarm algorithm (SSA), and the particle swarm optimization (PSO). In the study case, the power system consists of six thermal power plants (TPs), two wind farms, and two SPs. In addition, the variation of load demand over 24 hours of one day is applied. DO and SSA can achieve the best cost of $15443.0753 for the first system, but PSO cannot. However, DO is the most stable method reaching the standard deviation of 0.0184 for fifty runs but that of SSA and PSO is about 1.0439 and 8.9664. For the second system, DO can reach smaller cost than PSO by $11.17, $137.74 and $323.09 for the best, mean and worst solutions among fifty found solutions. As a result, DO is strongly recommended for solving the ELD problem.

Conceptual Design of Solid-State Li-Battery for Urban Air Mobility

The negative impact of internal combustion engines on the environment is a major concern in metropolitan areas due to the continued rapid growth and high overall level in the number of vehicles, population, and traffic congestion. Electric vertical take-off and landing (eVTOL) aircraft promises a new era for urban regional transportation and air mobility to address the challenges mentioned above. Nonetheless, providing electrical energy storage systems, like batteries, is one of the key issues with such aircraft. Here, the non-flammable technology of all-solid-state Li batteries with high theoretical gravimetric energy is an attractive option. Modelling allows for a knowledge-driven assessment of the potential of this technology. We here used a combination of a pseudo-2-dimensional cell model with a microstructure surrogate model approach to acquire a better understanding of the effect of the cathode microstructure on the internal process limitations. This model is incorporated into a global optimisation algorithm to predict optimum battery size with respect to the dynamic load demand of eVTOL. When carbon black and active materials are premixed, the battery performs better than when solid electrolyte and active materials are premixed, particularly for low amounts of carbon black in the cathode combination, i.e., 5%. Further, results indicate that future electrification of transportation powertrains would necessitate optimising the composition and distribution of electrode components to fulfil the high demands for power and energy density. By enhancing transport through the microstructure and improving the material’s intrinsic conductivity, it is possible to significantly increase the effective diffusivity and conductivity of ASSB, and hence the mission range.

Power management of grid-connected PV wind hybrid system incorporated with energy storage system

Renewable Energy Sources (RES) such as solar photovoltaic (PV) and wind-based generation cannot meet dynamic load demand all the time because of their intermittent nature. Battery Energy Storage System (BESS) is integrated with RES to meet dynamic load demands. Proper power management is needed for the efficient and reliable performance of the system. This paper presents power management of PV-Wind- Battery hybrid system for both grid-connected and islanded modes of operation as well. The power balance is maintained by a power management system (PMS) under different environmental conditions and load conditions, and modes of operation. The control method for state-of-charge (SOC) and battery charge/discharge is applied to ensure efficient performance and safe operation of BESS. Different cases, such as surplus/deficit power available from RES with respect to load demand and battery capacity, have been considered and carried out to verify the performance of PMS using the MATLAB/Simulink platform.

Modelling spatiotemporal impact of flash floods on power distribution system and dynamic service restoration with renewable generators considering interdependent critical loads

AbstractIn recent decades, flash floods have become more common because of climate change and are considered a substantial risk for many cities worldwide. This catastrophic natural hazard presents a significant threat to critical infrastructure in urban areas, particularly the power distribution system. As modern societies are much more dependent on electrical energy these days, it is essential and imperative to make existing distribution systems resilient against flash flooding. Although researchers in this area have proposed various algorithms to impart resilience to a distribution system, however, the focus in these works is on wind‐related events such as hurricanes, cyclones, and windstorms. Therefore, here, the spatiotemporal effects of a flash flood on the distribution system are modelled using a grid‐based hydrodynamic model. The evolving line faults are then included in the proposed resilience‐oriented time horizon‐based service restoration model that also considers dynamic load demand, heavy uncertainties related to renewable generation, and interdependence among critical loads. Finally, the resilience of the distribution system's response is assessed using an operational resilience metric. The efficacy of the proposed framework is evaluated on IEEE 33‐bus and 69‐bus systems and the results show that the model provides an efficient restoration solution despite increased complexity caused by varying conditions.

PowRL: A Reinforcement Learning Framework for Robust Management of Power Networks

Power grids, across the world, play an important societal and economical role by providing uninterrupted, reliable and transient-free power to several industries, businesses and household consumers. With the advent of renewable power resources and EVs resulting into uncertain generation and highly dynamic load demands, it has become ever so important to ensure robust operation of power networks through suitable management of transient stability issues and localize the events of blackouts. In the light of ever increasing stress on the modern grid infrastructure and the grid operators, this paper presents a reinforcement learning (RL) framework, PowRL, to mitigate the effects of unexpected network events, as well as reliably maintain electricity everywhere on the network at all times. The PowRL leverages a novel heuristic for overload management, along with the RL-guided decision making on optimal topology selection to ensure that the grid is operated safely and reliably (with no overloads). PowRL is benchmarked on a variety of competition datasets hosted by the L2RPN (Learning to Run a Power Network). Even with its reduced action space, PowRL tops the leaderboard in the L2RPN NeurIPS 2020 challenge (Robustness track) at an aggregate level, while also being the top performing agent in the L2RPN WCCI 2020 challenge. Moreover, detailed analysis depicts state-of-the-art performances by the PowRL agent in some of the test scenarios.

Dynamic progressive collapse response of multi-storey frame structures with masonry infills

The response of reinforced concrete (RC) frame building structures to exceptional events like explosions or impacts causing the loss of a primary structural element depends on the robustness of the structural configuration. In the case of a sudden column loss, the resisting mechanism of the involved spans substantially changes, while a progressive collapse mechanism can develop under the arising dynamic loads. The presence of masonry infill walls can substantially modify the overall response to a sudden column loss scenario. In this context, this paper investigates the response of reinforced concrete frame structures undergoing instantaneous column losses in order to assess the influence of masonry infills on the progressive collapse response under dynamic load demands. A recently formulated equivalent-strut macro-modelling approach is employed to reproduce the mechanical interaction between infill walls and the frames. A ten-storey, six-bays 2D reinforced concrete frame is selected as a case study structure considering different reinforcement layouts (seismic or non-seismic design) and column loss scenarios (central column or corner column loss). The simulations are carried out using the fiber-section beam/column elements available in the OpenSees software platform, as they can account for the arching mechanism developing in the post-cracked regime. The dynamic responses of the case-study tests to the sudden column loss scenarios are assessed with and without the inclusion of masonry infills within the structural models. Results demonstrate that masonry infills introduce a substantial modification of the resisting mechanism and of the dynamic response, limiting the propagation of progressive collapse in most of the considered cases.

Optimizing dynamic electric ferry loads with intelligent power management

In recent years, there has been an increasing shift towards using environmentally friendly renewable resources in marine vessels, replacing traditional diesel generators. However, one of the main challenges faced in renewable energy-driven marine vessels is dynamic load management. The feasibility of a renewable-powered electric marine vessel largely depends on the optimal utilization of renewable resources, and storage is an essential component of the marine electric vessel. This paper proposes a two-stage power management system (PMS) for an electric ferry powered by the fuel cell and battery energy storage systems (BESS). The primary objective of the proposed PMS is to ensure a balance between the generated power and the ferry load by minimizing the consumption of hydrogen (H2) fuel. The first stage of the PMS employs particle swarm optimization (PSO), bacterial foraging optimization (BFO), and a hybrid PSO-BFO algorithm to optimize the fuel cell and battery capacity. This is done so that the generated power can follow the load demand. The second stage of the PMS utilizes the Mamdani rule-based fuzzy logic system (FLS) to match the load demand with the generated power. The hybrid PSO-BFO algorithm optimizes the fuzzy control parameters to meet the dynamic load by ensuring optimal H2 fuel consumption and battery state of charge (SOC). To obtain optimal values, the load profile of a conventional ferry is used for the proposed PMS. Based on the optimization results, the optimal capacities are found to be 318 kWh and 317.64 kWh for the fuel cell and BESS, respectively, which are obtained using the hybrid PSO-BFO algorithm. The optimal value of H2 fuel consumption during cruising is found to be 18 kg. A simulated model-based approach validates the operation of the proposed PMS. The proposed PMS ensures optimal H2 fuel consumption and battery SOC while meeting the dynamic load demands of the ferry. The results obtained demonstrate the effectiveness of the proposed PMS in optimizing the renewable energy-driven marine vessel power system.

Capacity assessment and scheduling of battery storage systems for performance and reliability improvement of solar energy enhanced distribution systems

The intuition of the utilities in the power distribution system is to provide premium quality electricity to the consumers uninterruptedly and environment friendly. The inclusion of renewable energy sources (RES) in association with conventional power generation has undoubtedly made the distribution system clean and green to meet the dynamic load demand but invited significant instability and complexity to the system. The traditional power supply and stochastic photo voltaic (PV) generation can be managed in an organized way to meet the wide variability in power demand by using battery storage systems (BSSs). This paper presents a novel strategy to optimally determine the size and charging discharging scheduling of BSSs in a distribution system (DS) to enhance its performance and reliability. The DS technical performance and reliability improvement are collectively investigated using the weight-aggregated particle swarm optimization (WAPSO) technique. The proposed strategy has been implemented in 28-bus and 69-bus radial DS over the various seasons. The DS minimum voltage profile and reliability improvement have been performed by minimizing the SADPL, SADD, SAENS through optimal BSSs size and optimized charging discharging scheduling. Through the proposed strategy the percentage reductions in SADPL, SADD, SAENS in the 28-bus DS are found to be 0.18 %, 13 %, and 16 % respectively which expresses the efficacy of the present work. The comparative analysis of the outcomes, optimal power injection by BSSs with optimized scheduling, and sensitivity analysis has been performed.

Development of fuzzy logic-based demand-side energy management system for hybrid energy sources

Demand-side energy management techniques, such as load shielding, shifting, and delaying appliance operation during peak periods, are typically used to reduce electricity costs at the expense of users’ comfort. To address these challenges, especially where operational delays are unacceptable, distributed generation (DG) is frequently incorporated into the grid system to improve power balance and total energy costs. However, dynamic load demands and varying outputs from renewable DG sources such as solar photovoltaic (PV) systems make energy management in microgrids (MGs) extremely challenging. Moreover, most of the existing studies in this domain focus on objective functions that are geared on optimising the economic balance between cost and value of MG operation over a certain time period. Nevertheless, research that took into consideration the stochastic behaviour of DG’s subsystems in addition to cost and benefit of MG operation are still limited. This current study proposed a fuzzy logic control (FLC) integrated energy management system (EMS) for commercial loads with hybrid grid-solar PV/battery energy system. The proposed technique intelligently selects energy sources using the grid energy cost and the state of charge (SoC) of the solar PV/battery at any time of the day. The EMS operate the loads at a reduced cost without any operational delay or shifting. The system was implemented in the MATLAB/Simulink environment, and the techno-economic feasibility of energy cost savings was investigated by comparing the developed scheme with the Homer hybrid energy system model for a hotel building. The developed EMS reduced energy costs by an average of 11.87 % per day and 7.94 % over a 20-year lifetime.

Comprehensive sustainability assessment of a novel solar-driven PEMEC-SOFC-based combined cooling, heating, power, and storage (CCHPS) system based on life cycle method

Combined cooling, heating, and power systems powered by renewable energy could efficiently reduce the dependency on fossil fuels and decrease greenhouse gas emissions. This study presents a novel solar-driven proton exchange membrane electrolysis cell and solid-oxide fuel cell-based combined cooling, heating, power, and storage (CCHPS) system integrated with the parabolic trough photovoltaic-thermal (PTPVT) collector. The efficient PTPVT collector is employed to effectively generate solar electricity and thermal energy concurrently. A robust energy management strategy for optimal utilization of solar energy is proposed to smooth the solar energy fluctuations and proactively respond to the user's dynamic load demands. With the entropy weight method, a comprehensive sustainability quantitative analysis based on the life cycle method, which encompasses eleven indicators covering energy, environmental, and economic multi-attributes, is conducted to evaluate the sustainability performance of the proposed system. Meanwhile, the operating characteristics of proactively responding to the user's dynamic load demands under different operating modes and the effects of key parameters are also investigated. The results demonstrate that when the receiver side length of the PTPVT varies from 0.04 m to 0.08 m, the electric efficiency of the PTPVT declines from 24.19% to 22.93%, and the grid electricity consumption of the hybrid system increases by 16.62 MWh per year. Besides, the annual investment cost, annual net saving cost, and simple payback period are demoted by 709.52 $, 1233.01 $ and 0.09 year, respectively. The composite sustainability index of the hybrid system with a 0.04 m receiver side length of the PTPVT illustrates optimal comprehensive sustainability performance with 0.998.

Day-Ahead Load Demand Forecasting in Urban Community Cluster Microgrids Using Machine Learning Methods

The modern-day urban energy sector possesses the integrated operation of various microgrids located in a vicinity, named cluster microgrids, which helps to reduce the utility grid burden. However, these cluster microgrids require a precise electric load projection to manage the operations, as the integrated operation of multiple microgrids leads to dynamic load demand. Thus, load forecasting is a complicated operation that requires more than statistical methods. There are different machine learning methods available in the literature that are applied to single microgrid cases. In this line, the cluster microgrids concept is a new application, which is very limitedly discussed in the literature. Thus, to identify the best load forecasting method in cluster microgrids, this article implements a variety of machine learning algorithms, including linear regression (quadratic), support vector machines, long short-term memory, and artificial neural networks (ANN) to forecast the load demand in the short term. The effectiveness of these methods is analyzed by computing various factors such as root mean square error, R-square, mean square error, mean absolute error, mean absolute percentage error, and time of computation. From this, it is observed that the ANN provides effective forecasting results. In addition, three distinct optimization techniques are used to find the optimum ANN training algorithm: Levenberg–Marquardt, Bayesian Regularization, and Scaled Conjugate Gradient. The effectiveness of these optimization algorithms is verified in terms of training, test, validation, and error analysis. The proposed system simulation is carried out using the MATLAB/Simulink-2021a® software. From the results, it is found that the Levenberg–Marquardt optimization algorithm-based ANN model gives the best electrical load forecasting results.

Research on the variation of current density distribution in a commercial-size proton exchange membrane fuel cell under dynamic gas operation parameters

Proton exchange membrane fuel cells are considered as a promising alternative energy conversion device and its performance is largely affected by operation parameters. Among these parameters, stoichiometric ratio and back pressure can be properly controlled in practice and have a significant influence on the performance, but the mass transfer process in a fuel cell is seriously restricted. Therefore, the variation of overall performance and current density distribution of a commercial-size proton exchange membrane fuel cell under dynamic gas operation parameters especially during transient process is detailly investigated in this paper. Experiments are conducted with dynamic gas operation parameters using segmented cell technology. Cathode stoichiometric ratio serves as a better operation parameter than back pressure when attempting to affect the cell performance timely and effectively. Effect of back pressure drop under different situations are analyzed. During a short transient process, a large increase of cathode stoichiometric ratio leads to an instant performance increase of area far away from cathode inlet and thereby cause an increase of cell performance. This work leads to suggestions on the control strategy during dynamic load demands and lays a foundation for further study into the durability under variable gas operation parameters of the fuel cell operation.

Influence of energy management strategies and storage devices on the techno-enviro-economic optimization of hybrid energy systems: A case study in Western Australia

The evolution and technological growth of battery energy storages have added a certain mobility to the global development and dispatch of hybrid renewable systems subsiding the supply uncertainty of these systems arising from the inherent source-intermittency. However, the existing technical diversity among those battery storages calls for the assessment of how different technologies affect an optimal renewable mix and its techno-enviro-economic performance while meeting highly dynamic load demands. This study considers three different electrochemical energy storages, namely lead acid, lithium-ion and vanadium redox flow battery systems to be commissioned into stand-alone hybrid energy systems comprising different proportions of solar photovoltaic, wind turbine, and micro gas turbine to serve the electricity demand of an Australian community. Each of these hybrids are subjected to two different energy management strategies, and optimized using non dominated sorting genetic algorithm II method with the multi-objectives of minimizing cost of energy ($/kWh) and life cycle emission (kg CO2-eq/kWh) under a predefined reliability constraint, loss of power supply probability. Moreover, the impacts of different battery technologies and dispatch strategies have been assessed considering different socioeconomic, technical and environmental performance indicators. Results indicate that the hybrid system with cyclic charging strategy gives the lower energy cost with lifecycle emissions slightly higher than the load following strategy options. The vanadium redox flow-based hybrid options offer the lowest cost of energy (0.126–0.187$/kWh) and the lifecycle emissions (46,258–104,664 kg CO2-eq/yr) of all. The sensitivity analysis reveals that the cost of energy of the hybrid options declines at the cost of reliability and lifecycle emissions. This study provides vital information for energy planners to decide which battery technology to choose and under which dispatch strategy it performs better when the overall technical, economic, environmental and social perspectives are in play.

A Modified Control Method for Grid Connected Multiple Rooftop Solar Power Plants

This article proposes an enhanced control strategy for a microgrid consisting of multiple rooftop solar photovoltaic sources. These sources are of different power ratings and intermittent in nature. The microgrid is flexible to function either in islanded mode or in grid connected mode. It affects power management and hampers the power quality in microgrid. The proposed control scheme enhances the power quality of the microgrid by providing reactive power compensation to local loads. Thus, it reduces the burden on utility grid. The proposed control technique establishes a priority-based policy for reactive and active power compensation under local demand variance. A smooth and automated transition of microgrid between islanded and grid connected modes is achieved. This seamless transition of the system between two modes avoids the transient in the system. In islanded mode, the proposed control scheme ensures improved voltage regulation under dynamic load demand. It also ensures a minimum burden on the voltage source. Also, the proposed control scheme maintains the power factor of the system near to unity. The system performance is validated experimentally under a number of various operating conditions such as dynamic load variation, grid condition, automated transition, intermittent power generation in real time simulator.

Optimal Energy Management of a Double-Tracking Grid-Connected Photovoltaic with Battery System for a Microbrewery

Currently, the production of craft beer in microbreweries has become very popular. This craft beer production process is energy intensive due heating and cooling equipment involved. Most of these breweries are classified as commercial loads which are subjected to the applicable commercial time-of-use tariff from the utility company. Renewable energy sources can also be used to assist the breweries in reducing their reliance on the energy from the grid. However, these systems show a common disadvantage of not always meeting the energy demand during the periods where the resources are not available. In this paper, an optimal energy management model of a 5 kWp grid-connected photovoltaic, using a double tracking system with battery storage, is proposed to reduce the microbrewery’s reliance on the grid. For this purpose, a mathematical model describing the system’s variables, objective function, and constraints are developed. Thereafter, the performance of the developed model is simulated and analyzed using the dynamic load demand of a microbrewery brewery as a case study in the South African context. For the selected brewery, the simulation results have shown that for the solar resources as well as applicable grid tariff; up to 53.5% daily operation cost reduction can be achieved when using the proposed system as comped to the usage of the grid alone.

Dynamic economic emission dispatch of thermal-wind-solar system with constriction factor-based particle swarm optimization algorithm

PurposeDynamic economic and emission dispatch (DEED) aims to optimally set the active power generation with constraints in a power system, which should target minimum operation cost and at the same time minimize the pollution in terms of emission when the load dynamically changes hour to hour. The purpose of this study is to achieve optimal economic and emission dispatch of an electrical system with a renewable generation mix, consisting of 3-unit thermal, 2-unit wind and 2-unit solar generators for dynamic load variation in a day. An improved version of a simple, easy to understand and popular optimization algorithm particle swarm optimization (PSO) referred to as a constriction factor-based particle swarm optimization (CFBPSO) algorithm is deployed to get optimal solution as compared to PSO, modified PSO and red deer algorithm (RDA).Design/methodology/approachDifferent model with and without wind and solar power generating systems; with valve point effect is analyzed. The thermal generating system (TGs) are the major green house gaseous emission producers on earth. To take up this ecological issue in addition to economic operation cost, the wind and solar energy sources are integrated with the thermal system in a phased manner for electrical power generation and optimized for dynamic load variation. This DEED being a multi-objective optimization (MO) has contradictory objectives of fuel cost and emission. To get the finest combination of the two objectives and to get a non-dominated solution the fuzzy decision-making (FDM) method is used herein, the MO problem is solved by a single objective function, including min-max price penalty factor on emission in the total cost to treat as cost. Further, the weight factor accumulation (WFA) technique normalizes the pair of objectives into a single objective by giving each objective a weightage. The weightage is decided by the FDM approach in a systematic manner from a set of non-dominated solutions. Here, the CFBPSO algorithm is applied to lessen the total generation cost and emission of the thermal power meeting the load dynamically.FindingsThe efficacy of the contribution of stochastic wind and solar power generation with the TGs in the dropping of net fuel cost and emission in a day for dynamic load vis-à-vis the case with TGs is established.Research limitations/implicationsCost and emission are conflicting objectives and can be handled carefully by weight factors and penalty factors to find out the best solution.Practical implicationsThe proposed methodology and its strategy are very useful for thermal power plants incorporating diverse sources of generations. As the execution time is very less, practical implementation can be possible.Social implicationsAs the cheaper generation schedule is obtained with respect to time, cost and emission are minimized, a huge revenue can be saved over the passage of time, and therefore it has a societal impact.Originality/valueIn this work, the WFA with the FDM method is used to facilitate CFBPSO to decipher this DEED multi-objective problem. The results reveal the competence of the projected proposal to satisfy the dynamic load demand and to diminish the combined cost in contrast to the PSO algorithm, modified PSO algorithm and a newly developed meta-heuristic algorithm RDA in a similar system.

Daily peak-based short-term demand prediction using backpropagation combined to chi-squared distribution

Abstract An efficient and economic scheduling of power plants relies on an accurate demand forecast especially for the short-term due to its tight relation to power markets and trading operations in interconnected power systems. A slight deviation of load prediction from real demand could engender the start-up of a conventional power station which could be either time-consuming or requiring expensive combustible, a deviation that could interfere as well with renewables intermittency and demand response strategies. Hence, load forecasting still a challenging subject because of the various transformations that the energy sector undergoes and that directly impact the demand profile shape. Therefore, conceiving dynamic load demand forecast approaches will permit utilities save money in different vertical structures and regulation schemes. In this paper, we propose a novel approach for short-term demand prediction valid for normal and special days to address the impact of climate changes along with events occurrence on forecast accuracy. This approach is based on the prediction of hourly loads, established on the daily peak load prediction using backpropagation combined to chi-squared method for weighting historical data to enhance the training process. Obtained results from extensive testing on the Moroccan’s power system confirm the strength of the developed approach, that improved the forecast accuracy by a range of 1.1–4% compared to the existing methods.

Comparative Performance of a Hybrid Renewable Energy Generation System with Dynamic Load Demand

This article presents the modeling and simulation of a hybrid generation system, which uses solar energy generation, wind energy, and the regulation of a proton exchange membrane (PEM) cell to raise the demanded load, empowering the use of these hydride systems worldwide. This generation system was simulated for different locations in Puerto Bolivar (Colombia), Bremen (Germany), Beijing (China), and Texas (USA), for two demand profiles. The data used for the simulation was calculated using the mathematical solar model proposed by Beistow and Campbell for solar radiation. In contrast, for the wind resource evaluation, the Weibull probability distribution was used to calculate the most probable wind speed for each day, according to the historical data for each of the studied locations. Considering these data, the process transfer functions were used for tuning the control parameters for the hydrogen and oxygen production system. For the evaluation of the performance of these controllers, the indices of the absolute value of the error (IAE), the integral of the square of the error (ISE), the integral of the absolute value of the error for time (ITAE), and the integral of the square of the error for time (ITSE) were used. It was found that in the second load profile studied, better performance of the ITSE performance parameter was obtained, with stabilization times lower than those of the first profile.