Modified deep learning and reinforcement learning for an incentive-based demand response model
یادگیری عمیق اصلاح شده و یادگیری تقویتی برای یک مدل پاسخ تقاضای مبتنی بر انگیزه-2020
Incentive-based demand response (DR) program can induce end users (EUs) to reduce electricity demand during peak period through rewards. In this study, an incentive-based DR program with modified deep learning and reinforcement learning is proposed. A modified deep learning model based on recurrent neural network (MDL-RNN) was first proposed to identify the future uncertainties of environment by forecasting day-ahead wholesale electricity price, photovoltaic (PV) power output, and power load. Then, reinforcement learning (RL) was utilized to explore the optimal incentive rates at each hour which can maximize the profits of both energy service providers (ESPs) and EUs. The results showed that the proposed modified deep learning model can achieve more accurate forecasting results compared with some other methods. It can support the development of incentive-based DR programs under uncertain environment. Meanwhile, the optimized incentive rate can increase the total profits of ESPs and EUs while reducing the peak electricity demand. A short-term DR program was developed for peak electricity demand period, and the experimental results show that peak electricity demand can be reduced by 17%. This contributes to mitigating the supply-demand imbalance and enhancing power system security.
Keywords: Demand response | Modified deep learning | Reinforcement learning | Smart grid
Zero-net energy management for the monitoring and control of dynamically-partitioned smart water systems
مدیریت انرژی صفر خالص برای نظارت و کنترل سیستم های اب هوشمند تقسیم شده -2020
The optimal and sustainable management of water distribution systems still represent an arduous task. In many instances, especially in aging water net-works, pressure management is imperative for reducing breakages and leakages. Therefore, optimal District Metered Areas represent an effective solution to decreasing the overall energy input without performance compromise. Within this context, this paper proposes a novel adaptive management framework for water distribution systems by reconfiguring the original network layout into (dynamic) district metered areas. It utilises a multiscale clustering algorithm to schedule district aggregation/desegregation, whilst delivering energy and supply management goals. The resulting framework was tested in a water utility network for the simultaneously production of energy during the day (by means of the installation of micro-hydropower systems) and for the reduction of water leakage during the night. From computational viewpoint, this was found to significantly reduce the time and complexity during the clustering and the dividing phase. In addition, in this case, a recovered energy potential of 19 MWh per year and leakage reduction of up to 16% was found. The addition of pump-as-turbines was also found to reduce investment and maintenance costs, giving improved reliability to the monitoring stations. The financial analyses to define the optimal period in which to invest also showed the economic feasibility of the proposed solution, which assures, in the analysed case study, a positive annual net income in just five years. This study demonstrates that the combined optimisation, energy recovery and creation of optimized multiple-task district stations lead to an efficient, resilient, sustainable, and low-cost management strategy for water distribution networks.
Keywords: Water distribution systems | Micro-hydropower systems | Sustainable and smart cities | Water-energy nexus | Water leakage reduction | Financial return-on-investment
Ensuring the reduction in peak load demands based on load shifting DSM strategy for smart grid applications
تضمین کاهش تقاضای بار اوج بر اساس تغییر استراتژی DSM برای کاربردهای شبکه هوشمند-2020
In recent year the concept of prosumers (energy producer as well as the consumer) is becoming more popular, and on the other side, demand response has gained attention especially in the smart and micro grid systems. In such power networks, the behaviors of prosumers are highly variable due to many factors and few are price depended, incentive depended etc., Due to the highly dynamic nature of the prosumers, the peak load management is becoming crucial in the power system operation and control especially in smart grids, in which demand side management (DSM) application thought to be useful. This paper presents a simulation study on the role of DSM in the peak load management for a residential community. Here, load shitting-based DSM technique is used. This study considered the daily consumption patterns (hour wise) of electricity using the four types of electric loads. Results showed a considerable decrease in the peak load when compared to the load patterns before applying DSM. The average demand per day in summer is 4.521 kW, and in winter is 3.871 kW. The summary of peak load demands per day in kW without DSM are 14.712 kW, and 18.18 kW for summer and winter respectively. With the load shifting based DSM technique, the peak load per day are reduced to 9.6 kW in the summer season and 9.672 kW in the winter season.
Keywords: Smart grid | demand side management | load shifting | peak loads | load management | energy management
Complementarity modeling of monthly streamflow and wind speed regimes based on a copula-entropy approach: A Brazilian case study
مدل سازی مکمل رژیم های ماهانه جریان و سرعت باد بر اساس یک رویکرد کوپل-آنتروپی: یک مطالعه موردی برزیل-2020
Wind power energy has been showing significant growth in installed capacity around the world. This opportunity presents big challenges to operate power systems with high wind power penetration levels, considering the variability and intermittent behavior of this type of power source. To reduce uncertainties associated with this kind of power systems, researchers have explored the integration of wind power energy with other renewable energy sources, like solar and hydropower. For instance, the integration of wind and hydro systems can deal with the spatial and temporal complementarity of hydrological and wind regimes to produce energy. Therefore, it is necessary to consider the stochastic behavior and the dependence structures between these variables to define better operational policies. This study explores the spatial correlation of hydrological and wind regimes in different regions of Brazil and defines an entropy-copula-based model for the joint simulation of monthly streamflow and wind speed time series to evaluate the potential integration of hydro and wind energy sources. The proposed model showed a good adherence to the periodic behavior for both variables, and the results indicate that simulated scenarios preserved statistical features of historical data
Keywords: Hydro-wind complementary | Renewable energy | Stochastic modeling
An IGDT-based risk-involved optimal bidding strategy for hydrogen storagebased intelligent parking lot of electric vehicles
یک استراتژی مناقصه بهینه مبتنی بر خطر IGDT برای ذخیره سازی هیدروژن مبتنی بر پارکینگ هوشمند وسایل نقلیه برقی-2020
In a near future, electric vehicles (EVs) will constitute considerable part of transportation systems due to their important aspects such as being environment friendly. To manage high number of EVs, developing hydrogen storage-based intelligent parking lots (IPLs) can help power system operators to overcome caused problems by high penetration of EVs. In this work, a new method is applied to get optimal management of IPLs in an uncertain environment and provide optimal bidding curves to take part in power market. The main purpose of this work is to get optimal bidding curves with considering power price uncertainty and optimal operation of IPLs. To model uncertainty of power price in the power market and develop optimal bidding curve, the opportunity, deterministic and robustness functions of the information gap decision theory (IGDT) technique has been developed. Obtained results has been presented in three strategies namely risk-taker, risk-neutral, and risk-averse corresponding to opportunity, deterministic, and robustness functions of the IGDT technique. In order to demonstrate the effects of demand response program (DRP), each strategy is optimized with and without DRP cases. The mixed-integer non-linear programming model is used to formulate the proposed problem which is solved using the GAMS optimization software under DICOPT solver.
Keywords: Social welfare of owners of electric vehicles | Intelligent parking lot | Optimal bidding curve | Power price policy | IGDT technique | Energy management and business
Model predictive energy management in hybrid ferry grids
مدل مدیریت پیش بینی انرژی در شبکه های کشتی ترکیبی-2020
High performance and cost-effective ferry boats are of capital interest for customers and marine industry companies. On the other hand, the traditional ferry boats, operated by diesel generators, spatter the atmosphere with CO2 emissions and detrimental particles. Hence, electric propulsion in marine applications, especially in ferry vessel systems, has gained a lot of attention during the last decade as a promising technology to decrease fuel consumption and emissions. However, one of the main issues in the electric ferries (E-Ferry) is to keep the voltage and frequency within an acceptable range according to the large dynamic load fluctuations. In order to solve this issue, this paper presents a model predictive energy management based on a modified black hole algorithm (BHA) for the hybrid E-Ferry systems. Finally, to study the efficiency of our proposal, we run a real-time simulation using the d-Space simulator and compare the effect of the prediction horizon on the system performance.
Keywords: Marine power system | Model predictive control (MPC) | Electric ferry-system | Fuel cell technology | Black hole algorithm (BHA)
A new stochastic gain adaptive energy management system for smart microgrids considering frequency responsive loads
یک دستاورد تصادفی جدید سیستم مدیریت انرژی تطبیقی برای میکروگریدهای هوشمند با توجه به بارهای پاسخگو فرکانس-2020
Islanded microgrids as flexible, adaptive and sustainable smart cells of distribution power systems should be operated in accordance to both techno-economic purposes. Motivated by this need, the microgrid operators are in charge to elevate the active accommodation of both demand-side and supply-side distributed energy resources. To that end, in this paper, a new flexible frequency dependent energy management system is proposed through which distributed generators have time varying droop controllers with a gain-adaptive strategy. Besides to cope economically with uncertainty arise frequency excursions, a new, comfort-aware and versatile frequency dependent demand response program is mathematically formulated and conducted to the energy management system. It is aimed to co-optimize the microgrid energy resources such a way the day-ahead operational costs are managed subject to a secure frequency control portfolio. The presented model is solved using a two-stage stochastic programming and by a tractable efficient mixed integer linear programming approach. The simulation results are derived in 24-h scheduling time horizon and implemented on a typical test microgrid. The effectiveness of the proposed hourly gain assignment and frequency responsive load management program has been verified thoroughly by analyzing the results.
Keywords: Hierarchical control structure | Islanded microgrids | Droop gain scheduling | Frequency responsive loads | Two-stage stochastic optimization
Lazy reinforcement learning for real-time generation control of parallel cyber–physical–social energy systems
یادگیری تقویتی اهسته برای کنترل زمان واقعی تولید سیستم های انرژی موازی سایبری - فیزیکی - اجتماعی-2020
To learn human intelligence, the social system/human system is added to a cyber–physical energy system in this paper. To accelerate the configuration process of the parameters of the cyber–physical energy system, parallel systems based on artificial societies-computational experiments-parallel execution are added to the cyber–physical energy system, i.e., a parallel cyber–physical–social energy system is proposed in this paper. This paper proposes a real-time generation control framework to replace the conventional generation control framework with multiple time scales, which consist of long-term time scale, short-term time scale, and real-time scale. Since a lazy operator employed into reinforcement learning, a lazy reinforcement learning is proposed for the real-time generation control framework. To reduce the real simulation time, multiple virtual parallel cyber–physical–social energy systems and a real parallel cyber–physical–social energy system are built for the real-time generation control of large-scale multi-area interconnected power systems. Compared with a total of 146016 conventional generation control algorithms and a relaxed artificial neural network in the simulation of IEEE 10-generator 39-bus New-England power system, the proposed lazy reinforcement learning based realtime generation control controller can obtain the highest control performance. The active power between two areas and the systemic frequency deviation can be reduced by the lazy reinforcement learning, and the simulation results verify the effectiveness and feasibility of the proposed lazy reinforcement learning based real-time generation control controller for the parallel cyber–physical–social energy systems.
Keywords: Lazy reinforcement learning | Real-time generation control | Parallel cyber–physical–social energy systems | Artificial societies-computational | experiments-parallel execution | Unified time scale
Smart charging of electric vehicles considering photovoltaic power production and electricity consumption: A review
شارژ هوشمند وسایل نقلیه برقی با توجه به تولید انرژی فتوولتائیک و مصرف برق: بررسی-2020
Photovoltaics (PV) and electric vehicles (EVs) are two emerging technologies often considered as cornerstones in the energy and transportation systems of future sustainable cities. They both have to be integrated into the power systems and be operated together with already existing loads and generators and, often, into buildings, where they potentially impact the overall energy performance of the buildings. Thus, a high penetration of both PV and EVs poses new challenges. Understanding of the synergies between PV, EVs and existing electricity consumption is therefore required. Recent research has shown that smart charging of EVs could improve the synergy between PV, EVs and electricity consumption, leading to both technical and economic advantages. Considering the growing interest in this field, this review paper summarizes state-of-the-art studies of smart charging considering PV power production and electricity consumption. The main aspects of smart charging reviewed are objectives, configurations, algorithms and mathematical models. Various charging objectives, such as increasing PV utilization and reducing peak loads and charging cost, are reviewed in this paper. The different charging control configurations, i.e., centralized and distributed, along with various spatial configurations, e.g., houses and workplaces, are also discussed. After that, the commonly employed optimization techniques and rulebased algorithms for smart charging are reviewed. Further research should focus on finding optimal trade-offs between simplicity and performance of smart charging schemes in terms of control configuration, charging algorithms, as well as the inclusion of PV power and load forecast in order to make the schemes suitable for practical implementations.
Keywords: Photovoltaics | Electric vehicles | Electricity consumption | Smart charging | Energy management system | Charging optimization
Electricity demand forecasting for decentralised energy management
پیش بینی تقاضای برق برای مدیریت انرژی غیر متمرکز-2020
The world is experiencing a fourth industrial revolution. Rapid development of technologies is advancing smart infrastructure opportunities. Experts observe decarbonisation, digitalisation and decentralisation as the main drivers for change. In electrical power systems a downturn of centralised conventional fossil fuel fired power plants and increased proportion of distributed power generation adds to the already troublesome outlook for op- erators of low-inertia energy systems. In the absence of reliable real-time demand forecasting measures, effective decentralised demand-side energy planning is often problematic. In this work we formulate a simple yet highly effective lumped model for forecasting the rate at which electricity is consumed. The methodology presented focuses on the potential adoption by a regional electricity network operator with inadequate real-time energy data who requires knowledge of the wider aggregated future rate of energy consumption. Thus, contributing to a reduction in the demand of state-owned generation power plants. The forecasting session is constructed initially through analysis of a chronological sequence of discrete observations. Historical demand data shows behaviour that allows the use of dimensionality reduction techniques. Combined with piecewise interpolation an electricity demand forecasting methodology is formulated. Solutions of short-term forecasting problems provide credible predictions for energy demand. Calculations for medium-term forecasts that extend beyond 6-months are also very promising. The forecasting method provides a way to advance a novel decentralised informatics, optimisa- tion and control framework for small island power systems or distributed grid-edge systems as part of an evolving demand response service.
Keywords: Demand response | Decentralised | Grid edge | Time series forecasting