Rule-based Strategy Research Articles

Subsidizing Residential Low Priority Smart Charging: A Power Management Strategy for Electric Vehicle in Thailand

Government policies are crucial factors for supporting the growth of the electric vehicle (EV) industry—a growth that can be encouraged, for example, by subsidization designed to reduce the considerable anxiety stemming from the inconvenience of refueling at public charging stations. Subsidizing low priority charging for residential enables cost-effective load management for example controlling of EV charging power for grid reliability at the off-peak rate for 24 h. This solution provides the convenient recharging of EVs at home and prevents an expensive grid upgradation. To advance our understanding of the EV situation, this research used a regression model to forecast the growth rate of the EV market alongside the EV expansion policies in Thailand. The agreement between a policy and forecasting urges the government to prepare power system adequacy for EV loading. The analysis showed that power demand and voltage reduction in a typical low-voltage distribution system that assumes maximum EV loading constitute voltage violations. To address this limitation, this study proposed a rule-based strategy wherein low priority smart EV charging is regulated. The numerical validation of the strategy indicated that the strategy reduced power demand by 25% and 39% compared with that achieved under uncontrolled and time of use (TOU) charging, respectively. The strategy also limited voltage reduction and prolonged battery life. The study presents implications for policymakers and electricity companies with respect to possible technical approaches to stimulating EV penetration.

Bio-inspired chemical space exploration of terpenoids.

Many computational methods are devoted to rapidly generating pseudo-natural products to expand the open-ended border of chemical spaces for natural products. However, the accessibility and chemical interpretation were often ignored or underestimated in conventional library/fragment-based or rule-based strategies, thus hampering experimental synthesis. Herein, a bio-inspired strategy (named TeroGen) is developed to mimic the two key biosynthetic stages (cyclization and decoration) of terpenoid natural products, by utilizing physically based simulations and deep learning models, respectively. The precision and efficiency are validated for different categories of terpenoids, and in practice, more than 30000 sesterterpenoids (10 times as many as the known sesterterpenoids) are predicted to be linked in a reaction network, and their synthetic accessibility and chemical interpretation are estimated by thermodynamics and kinetics. Since it could not only greatly expand the chemical space of terpenoids but also numerate plausible biosynthetic routes, TeroGen is promising for accelerating heterologous biosynthesis, bio-mimic and chemical synthesis of complicated terpenoids and derivatives.

A Comprehensive Rule-Based Control Strategy for Automated Lane Centering System

A Comprehensive Rule-Based Control Strategy for Automated Lane Centering System

A Q-learning fuzzy inference system based online energy management strategy for off-road hybrid electric vehicles

In this paper, a Q-learning fuzzy inference system (QLFIS)-based online control architecture is proposed and applied for the optimal control of off-road hybrid electric vehicles (HEVs) to achieve better dynamic performance, fuel economy and real-time performance. A dynamic model, including a hybrid system, vehicle dynamics and road model, is established to obtain the state feedback according to the current driving environment under command. The optimal control strategy and objective function are both constructed by an adaptive network fuzzy inference system (ANFIS) due to its strong approaching ability. The fuzzy rules and parameters are trained online through the Q-learning algorithm and gradient descent method. This control framework provides a new control idea for the control of off-road vehicles. Without knowing the driving cycle in advance, it achieves a good control effect for different driving environments through online data collection and training. The QLFIS-based control strategy is compared to dynamic programming (DP)-based and rule-based strategies based on two different off-road driving cycles through simulation. The simulation results show that the vehicle dynamic performance and fuel economy are improved with respect to the rule-based strategy, while the calculation time is greatly reduced compared to that of the DP-based strategy.

Determination of vehicle working modes for global optimization energy management and evaluation of the economic performance for a certain control strategy

As the physical subject, determining vehicle operating modes is a prerequisite for implementing global optimization energy management. To avoid the case study of different vehicle configurations, a “kinetic/potential energy & onboard energy” conservation framework is proposed to determine vehicle working modes. Firstly, typical topologies and existing work modes for hybrid vehicles with different architectures are summarized. As a numerical method, the state space is meshed, which is restricted by introducing trip information. Then, a “kinetic/potential energy & onboard energy” conservation framework is established to determine the work mode between any reachable state points. By combining external factors, internal factors and additional factors reasonably and feasibly, various trigger conditions are generated to realize the one-to-one mapping between work mode and driving condition, which standardizes the DP optimizing process. Correspondingly, the stage cost and control are determined to achieve the optimal energy distribution. Finally, regarding DP strategy as a benchmark, multiple evaluation indexes are proposed to evaluate the utilization ratio of a control strategy to global trip information. An example is given to evaluate the optimal rule-based strategy. The higher the index is, the higher the similarity with the DP strategy is, and the higher the economic performance of the vehicle is.

Real-Time Torque-Split Strategy for P0+P4 Mild Hybrid Vehicles With eAWD Capability

The 48-V P0+P4 mild hybrid electric vehicles (MHEVs) have been drawing attention for their potential in fuel economy (FE) improvement and electric all-wheel-drive capability through a dual-motor system. This P0+P4 system, enabled by the addition of an extra P4 motor to an existing P0 MHEV, poses the new control problem of optimal torque-split among three components, namely, an internal combustion engine and P0/P4 motors. This study presents an effective real-time torque-split strategy for a 48-V P0+P4 MHEV. To include realistic operational constraints, we consider the longitudinal load transfer of the vehicle, nonlinear tire effects, and constraints on braking force distribution for vehicle safety. First, an optimal torque-split problem for the considered P0+P4 MHEV is formulated and solved with dynamic programming (DP). Then, based on the DP results, we propose a real-time-implementable torque-split strategy using an approximated adaptive equivalent consumption minimization strategy and a suboptimal braking force distribution strategy. The simulation results reveal that the proposed strategy can achieve about 99.1% and 97.7% of global optimality in terms of FE under training and validation driving cycles compared to the results by the DP. As a comparison, the rule-based strategy, as a benchmark, achieves 93.6% and 94.5% under the same drive cycles.

Deep Deterministic Policy Gradient-DRL Enabled Multiphysics-Constrained Fast Charging of Lithium-Ion Battery

Fast charging is an enabling technique for the large-scale penetration of electric vehicles. This article proposes a knowledge-based, multiphysics-constrained fast charging strategy for lithium-ion battery (LIB), with a consciousness of the thermal safety and degradation. A universal algorithmic framework combining model-based state observer and a deep reinforcement learning (DRL)-based optimizer is proposed, for the first time, to provide a LIB fast charging solution. Within the DRL framework, a multiobjective optimization problem is formulated by penalizing the over-temperature and degradation. An improved environmental perceptive deep deterministic policy gradient (DDPG) algorithm with priority experience replay is exploited to tradeoff smartly the charging rapidity and the compliance of physical constraints. The proposed DDPG-DRL strategy is compared experimentally with the rule-based strategies and the state-of-the-art model predictive controller to validate its superiority in terms of charging rapidity, enforcement of LIB thermal safety and life extension, as well as the computational tractability.

Optimal day-to-day scheduling of multiple energy assets in residential buildings equipped with variable-speed heat pumps

The largest parts of energy demand within the residential sector are used for space heating (SH), domestic hot water (DHW) and space cooling (SC). The thermal and electrical needs can be mainly covered by energy systems that consist of Photovoltaics (PVs), solar thermal collectors (STCs), heat pumps (HPs) and flexibility sources, e.g. battery energy storage (BES) and thermal energy storage (TES). In this paper, various control strategies for the optimal day-to-day operation of residential energy systems that consist of a variable-speed HP, STCs, PVs, as well as BES and TES units are examined. The proposed strategies are based on the concepts of self-consumption maximization (SCM) and time-of-use arbitrage (ToUA) considering priorities on BES and TES charging. A typical Greek single-family building is assumed examining multiple criteria for the assessment of the rule-based approaches. The results demonstrate that priority on TES charging can lead to higher system performance than on BES charging. Regardless of the number of ToU tariff zones, during off/mid-peak periods the upper energy needs of the SH/SC trajectory should be fulfilled only in case of excess PV power, otherwise the cost of imported energy increases significantly. Both SCM and ToUA strategies can lead to rates of self-consumption and self-sufficiency that deviate in average per about 4% from the optimal values. Moreover, the ToUA-based strategies can approach the minimum cost of imported energy with a relative increase of 22% compared to the optimum. However, the minimum thermal discomfort due to space temperature cannot be achieved without the prediction of the daily SH/SC demand. Furthermore, the proposed strategies can reach the minimum thermal discomfort due to DHW losses, while leading to lower BES degradation rates than the optimization. Finally, from the multi-objective optimization for the first year of system operation, it is verified that the optimal dimensioning of PV, BES and TES is considerably affected by the type of rule-based strategy selected.

Composite Non-Linear Control of Hybrid Energy-Storage System in Electric Vehicle

The underlying circuit control is a key problem of the hybrid energy-storage system (HESS) in electric vehicles (EV). In this paper, a composite non-linear control strategy (CNC) is proposed for the accurate tracking current/voltage of the fully-active HESS by combining the exact feedback linearization method and the sliding mode variable structure control technology. Firstly, by analyzing the circuit characteristics of HESS, the affine non-linear model of fully-active HESS is derived. Then, a rule-based energy management strategy (EMS) is designed to generate the reference current value. Finally, the HESS is linearized by the exact feedback linearization method, and the proposed CNC strategy is developed combined with sliding mode variable structure control technology to ensure fast response, high performance, and robustness. At the same time, the stability proof based on the Lyapunov method is given. Moreover, the performance of the CNC strategy is thoroughly investigated and compared with simulation studies with the traditional PI control and a modified sliding mode control, and its effectiveness under different driving conditions is fully verified.

An Optimal Fuzzy Logic-Based Energy Management Strategy for a Fuel Cell/Battery Hybrid Power Unmanned Aerial Vehicle

With the development of high-altitude and long-endurance unmanned aerial vehicles (UAVs), optimization of the coordinated energy dispatch of UAVs’ energy management systems has become a key target in the research of electric UAVs. Several different energy management strategies are proposed herein for improving the overall efficiency and fuel economy of fuel cell/battery hybrid electric power systems (HEPS) of UAVs. A rule-based (RB) energy management strategy is designed as a baseline for comparison with other strategies. An energy management strategy (EMS) based on fuzzy logic (FL) for HEPS is presented. Compared with classical rule-based strategies, the fuzzy logic control has better robustness to power fluctuations in the UAV. However, the proposed FL strategy has an inherent defect: the optimization performances will be determined by the heuristic method and the past experiences of designers to a great extent rather than a specific cost function of the algorithm itself. Thus, the paper puts forward an improved fuzzy logic-based strategy that uses particle swarm optimization (PSO) to track the optimal thresholds of membership functions, and the equivalent hydrogen consumption minimization is considered as the objective function. Using a typical 30 min UAV mission profile, all the proposed EMS were verified by simulations and rapid controller prototype (RCP) experiments. Comprehensive comparisons and analysis are presented by evaluating hydrogen consumption, system efficiency and voltage bus stability. The results show that the PSO-FL algorithm can further improve fuel economy and achieve superior overall dynamic performance when controlling a UAV’s fuel-cell powertrain.

Does this Answer Make Sense? Primary School Students and Adults Judge the Reasonableness of Computational Results in Context-Based and Context-Free Mathematical Tasks

This study investigates students’ and adults’ performance in judging reasonableness of computational results, namely reflecting on whether these results qualify as acceptable answers to mathematical tasks. Data was gathered via task-based questionnaires from 160 participants, evenly divided between fifth-graders and adults. Their responses to a systematically varied collection of context-free and context-based items shed light on their performance and strategies in relation to two interrelated aspects of reasonableness: number relationships and the effect of operations (internal reasonableness) and the practicality of answers (external reasonableness). The results revealed that students were better at utilising the former criterion compared to the latter, while for adults, the opposite was found. However, adults clearly outperformed students in both aspects. Task characteristics such as the involved numbers and operations, and the correctness or incorrectness of computation results, were found to be associated with fluctuations in performance, although the effect differed between context-free and context-based items. Algorithm- and rule-based strategies were more popular than sense-making ones especially among students, although only the latter type was correlated with increased correct response rates. Students often failed to obtain results that made sense considering real-life situations or the involved numbers and operations. Instead, they blindly trusted algorithms and rules, even when their use was inappropriate or insufficient. The findings highlight that to help students refine their ability to judge reasonableness, mathematics classrooms should prioritise the development of number sense and promote the search for connections between school mathematics and everyday life.

Power reserve predictive control strategy for hybrid electric vehicle using recognition-based long short-term memory network

For series hybrid electric vehicle (SHEV), due to the limitation of operating characteristic of engine, it is challenging to design an efficient power control strategy that can ensure instantaneous response of engine-generator set (EGS) to the sudden increase in demand power. In this paper, a power reserve predictive control strategy for SHEV is proposed. Firstly, a driving pattern recognition-based long short-term memory network is developed to predict future demand power. An improvement in the accuracy of this prediction is achieved by using a new time-series changing structure. Secondly, a novel method to regulate operation points of engine is presented, in which the instantaneous power output of engine can be responded to meet suddenly increased demand power by pre-regulating operating points according to the predicted power. Thirdly, the coordinative optimization for speed regulation of engine and power flow of vehicle is formulated in model predictive control framework considering multiple constraints of SHEV. Finally, the performance of the proposed strategy is both validated in simulation and hardware-in-loop test. The results show that the expected output power of EGS can be ensured, and the fuel economy can be improved by 9.16% and 5.91% over rule-based strategy, under the two test driving cycles, respectively.

Improved fuzzy logic control-based energy management strategy for hybrid power system of FC/PV/battery/SC on tourist ship

An improved fuzzy-based energy management strategy (EMS) is proposed for a tourist ship used hybrid power system with multiple power sources consisting of fuel cell(FC)/photovoltaic cell(PV)/battery(BAT)/super-capacitor(SC). The power demand from propeller and user terminal is afforded by the power sources connecting to power converters. To obtain more superior performance of the power system, the maximum power point tracking (MPPT) algorithm is employed to optimize the PV. Meanwhile, the improved fuzzy logic control based on dynamic programming (DP) associated with wavelet analysis and PI control are employed to achieve the output power optimal distribution and online control. In particular, the MPPT algorithm can improve the utilization of solar energy, and the SC can well absorb the high frequency power and reduce the fluctuation of the battery and FC that exhibits the potential of their lifetime extension. The FC outputs the high and stable power satisfying the ship's power demand even under the extreme work conditions. The developed model is able to illustrate well in the operation process of the hybrid power system governed by the proposed EMS. In addition, compared with the rule-based strategy, the improved fuzzy-based EMS can reduce 14.39% hydrogen consumption and keep the consistency of battery SOC. • Hybrid power system consists of fuel cell(FC)/PV/battery/SC used for tourist ship. • Electrical model of the hybrid power system with transient responses is presented. • Improved fuzzy-based energy management for the hybrid power system is proposed. • Fuzzy logic control based on dynamic programming and wavelet analysis is designed.

Real-time optimal EMS of adaptive charge sustenance for fuel cell hybrid buses based on driving characteristics recognition

To improve the service lifetime and fuel economy of fuel cell hybrid buses (FCHB), it is extremely important to establish a reasonable energy management strategy (EMS). Therefore, an optimization-based EMS for dual-energy systems is proposed in this paper. Specifically, the proposed strategy is realized via pontryagin’s minimum principle (PMP), which can solve the problems that include inaccurate estimation of the motor output power, the difficulty of SOC adaptive sustenance and real-time application of the algorithm. First, we analyze the driving characteristics of bus routes based on real bus driving data, and solve the optimal co-state values of the historical driving segments (DSs) by dividing driving cycle (DC) and DS. Then, the motor output power and the density-based spatial clustering of applications with noise (DBSCAN) algorithm are employed to predict the co-state value of the next DS. Thereafter, the real-time application of the PMP algorithm is achieved by using predicted co-state and analyzing the SOC adaptive sustenance item during the FCHB runs. The comparisons between real bus experiments and the simulations of five EMSs are conducted to validate the effectiveness. Results demonstrate that our strategy can reduce hydrogen consumption by 6.6% on average versus the rule-based strategy, the fluctuation range of SOC is less than 2%, the mean absolute error (MAE) between the initial and final SOC is 0.10%, and the fuel cell has less lifetime decay. Moreover, our strategy has the same excellent performance compared with the strategy under known driving conditions. In addition, the online computation time per step of the proposed real-time strategy is averaged at 34.8 ms, less than the sampling time interval 1 s. Therefore, the real-time performance of our strategy will contribute to the promotion and application of FCHBs.

A novel hybrid energy management strategy of a diesel-electric hybrid ship based on dynamic programing and model predictive control

The energy-saving characteristics of diesel-electric series hybrid ships largely depend on their energy management strategy. In this paper, a strategy that combines dynamic programing and model predictive control (DP-MPC) is proposed to solve the energy management problems of diesel-electric hybrid ships. The DP-MPC strategy has considered some typical working conditions of a ship, and the corresponding influence of white noise disturbance on the control strategy was studied. The simulation results show that the DP-MPC strategy has an excellent anti-interference capability. The control performance of the DP-MPC strategy is then further analyzed and compared with the rule-based logic threshold control strategy. The simulation results show that the proposed DP-MPC strategy can save 2.5% of the fuel consumption and has a better anti-interference capability than the rule-based control strategy.

Stochastic Model Predictive Control of Hybrid Energy Storage for Improving AGC Performance of Thermal Generators

In order to improve the automatic generation control (AGC) performance of thermal generators, this paper presents a stochastic model predictive control (SMPC) approach for a battery/flywheel hybrid energy storage system (HESS) to distribute power. The approach combines an adaptive Markov chain for power demand prediction of HESS, a scenario tree generation and model predictive control strategy. To develop an effective prediction model to deal with the randomness of a thermal generator in response to AGC command, a Markov chain is used to describe the randomness of the HESS power demand, and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a posteriori</i> information is used to adapt to the fluctuation of the AGC command. A scenario tree generation approach is proposed to make better use of the Markov probability matrix. Based on these efforts, an SMPC approach is proposed for HESS energy management. Simulation results show that the regulation performance of the proposed approach outperforms conventional approaches, and that its performance is close to the model predictive control strategy with prescient information of the future power demand. In addition, compared with other approaches such as rule-based strategies, it does less damage to the battery and yields higher annual average net benefits in the whole life cycle.

Market Making Strategy Optimization via Deep Reinforcement Learning

Optimization of market making strategy is a vital issue for participants in security markets. Traditional strategies are mostly designed manually, and orders are mechanically issued according to rules based on predefined market conditions. On one hand, market conditions cannot be well represented by arbitrarily defined indicators, and on the other hand, rule-based strategies cannot fully capture relations between the market conditions and strategies’ actions. Therefore, it is worthwhile to investigate how to incorporate deep reinforcement learning model to address those issues. In this paper, we propose an end-to-end deep reinforcement learning market making model, i.e., Deep Reinforcement Learning Market Making. It exploits long short-term memory network to extract temporal patterns of the market directly from limit order books, and it learns state-action relations via a reinforcement learning approach. In order to control inventory risk and information asymmetry, a deep Q-network is introduced to adaptively select different action subsets and train the market making agent according to the inventory states. Experiments are conducted on a six-month Level-2 data set, including 10 stock, from Shanghai Stock Exchange in China. Our model is compared with a conventional market making baseline and a state-of-the-art market making model. Experimental results show that our approach outperforms the benchmarks over 10 stocks by at least 10.63%.

The development of template-based facial expression perception from 6 to 15 years of age.

When perceiving emotional facial expressions, adults use a template-matching strategy, comparing the perceived face with a stored representation. A rejection of unnaturally exaggerated faces is characteristic of this strategy because the exaggerated expressions do not match the stored template. In contrast, a rule-based perceptual strategy (e.g., wide eyes indicate surprise) would be more tolerant of exaggeration. The current study uses exaggeration tolerance to test the expression perception strategies of children from 6 to 15 years of age. In Experiment 1, 62 (38 male) participants viewed pairs of happy or sad faces varying in exaggeration and selected the face that looked closest to how a happy (or sad) person really looks. With age, children became less likely to choose the more exaggerated expression. In Experiment 2, this result was replicated with each of the six basic emotions. Sixty-six children (26 male, 50 Caucasian, 10 mixed-race, four Indian, two unidentified) from 6 to 15 years of age completed the same experimental tasks as Experiment 1 for all six emotions. Again, with age children became less likely to choose the more exaggerated face. The results from both experiments suggest that the development of an adult-like template-matching strategy lasts into adolescence. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Optimized Energy Management Strategy for Hybrid Fuel Cell Powered Drones in Persistent Missions using Real Flight Test Data

AbstractThis paper proposes an optimized energy management strategy (EMS) for hybrid electric fuel cell/battery-based drones focusing on fuel economy while extending sources lifespans in persistent missions. An off-the-shelf drone fed by a 650W fuel cell is selected as a case study, where the power splitting is conventionally managed by a simple rule-based method. Then, a multi-objective genetic algorithm is used to optimize the proposed EMS parameters considering three scenarios regarding battery state of charge, namely charge sustaining, depleting, and increasing. Therefore, advantages of rule-based strategy and genetic algorithm are combined in an online EMS to fit on drone applications. Extensive simulation results demonstrate that the proposed approach allows power sources to operate within their rated area, prolonging their service life, and leading to 5.1% of fuel consumption reduction. Thus, the autonomy will be increased depending on the carried hydrogen quantity, and the world record can be extended by about 37min. It may also lead to benefit in the operating cost achieving 1450C during one fuel cell stack lifecycle. In fleet tasks, the benefit can be further multiplied.

Using HMM and Reinforcement Learning for Building Smarter Trading Strategies

Samit Ahlawat demonstrates the superior performance of AI-based trading strategies over static rule-based strategies. Two AI algorithms are considered for constructing the trading strategy: hidden Markov model (HMM) and asynchronous advantage actor-critic (A3C) method