Wind Uncertainty Research Articles

Research on key technologies of large-scale wind-solar hybrid grid energy storage capacity big data configuration optimization

Due to the uncertainty and randomness of large-scale wind and light, the output power of the power grid has great fluctuations. If it is directly connected to the grid, it will affect the main grid. In addition, when the grid switches between on-grid/off-grid operation modes, there will be power shortages, shocks and oscillations. The scientific and reasonable configuration of energy storage system capacity big data can reduce the load power shortage rate, improve the utilization rate of renewable energy, and ensure the reliable operation of the power grid. For this reason, the key technology of large-scale wind-solar hybrid grid energy storage capacity big data configuration optimization is studied. A large-scale wind-solar hybrid grid energy storage structure is proposed, and the working characteristics of photovoltaic power generation and wind power generation are analyzed, and the probability model of photovoltaic power generation, wind power generation and load, as well as the charging and discharging model of battery and super capacitor are established accordingly. On this basis, the optimization objective function is set, the constraints are determined, and the large-scale wind-solar hybrid grid energy storage capacity big data configuration optimization model is constructed. And the PSO algorithm is used to solve the model to realize the big data configuration optimization of large-scale wind-solar hybrid grid energy storage capacity. The research results show that the proposed method of large-scale wind-solar hybrid grid energy storage system has good power supply reliability and economy, and can effectively improve the utilization rate of renewable energy.

Robust active yaw control for offshore wind farms using stochastic predictive control based on online adaptive scenario generation

Subject to the inherent high uncertainty of wind, the prediction for its speed and direction may be insufficiently accurate, the resulting decision actions of active yaw control (AYC) may degrade the power gain. Therefore, this paper proposes a data-driven stochastic model predictive control (SMPC) using adaptive scenario generation (ASG) for offshore wind farm AYC. First, to build precise scenarios under the nonstationary variation of wind, an adaptive method based on Gaussian mixture model (GMM) clustering is proposed to allow online scenario identification with a compact construction. Specifically, GMM is constructed offline and two online mechanisms are developed for adaptive learning ability. To immunize the power maximization of AYC against prediction error, a data-driven robust optimization strategy is presented to realize SMPC based on generated scenarios. In order to enable real-time operation for large-scale wind farms, a novel parallel marine predator algorithm (PMPA) introduced population improvement strategy is developed to solve the robust problems with a quite lower computational burden. Finally, the simulation based on realistic wind data demonstrates the adaptive learning capacity of the proposed ASG. The result shows that the SMPC can improve the power gain by an average of 2.64% compared to the baseline predictive control.

Collaborative optimal scheduling of shared energy storage station and building user groups considering demand response and conditional value-at-risk

Energy storage devices can improve the utilization of clean energy and reduce the operating costs of building users. However, traditional energy storage is limited by its relatively low resource utilization and high cost. Firstly, to fully utilize the advantages of energy storage, a shared energy storage station (SESS) is introduced into the building user groups (BUGs). Second, this paper considers the incentive effect of flexible load participation in demand response (DR) on BUGs, quantifies the risky scheduling cost of wind uncertainty using conditional value-at-risk (CVaR), and then proposes a collaborative optimal scheduling model for BUGs and SESS considering DR and CVaR. Finally, the proposed model is verified by examples to achieve efficient complementation of SESS and BUGs, reduce the risk scheduling cost due to wind power uncertainty, and significantly reduce the capacity value of SESS and the electricity purchase of BUGs; meanwhile, this study carries out multi-perspective sensitivity analysis and CVaR analysis,which is informative for the refinement of the operating model of SESS and BUGs.

Short-term coordinated hybrid hydro-wind-solar optimal scheduling model considering multistage section restrictions

With the large-scale integration of wind and solar power in China, the consumption of these intermittent renewable energies is severely restricted by the capacity of the transmission channel, which leads to massive renewable energy curtailment. Therefore, it would be beneficial to use limited transmission channels to absorb as much renewable energy as possible. In this paper, we propose a chance constraint-based multistage nested hydro-wind-solar coordinated optimal scheduling model to aid peak shaving while ensuring maximum power generation. First, multistage partitioned section chance constraints are introduced to mitigate the power congestion of the transmission network. Then, based on the principle of using hydropower to complement the uncertainty of wind and solar power, the compensation chance constraints are considered. To quantify the uncertainty of wind and solar power, their prediction errors are analyzed using the Gaussian mixture model. Finally, the model is recast and linearized into a mixed integer linear programming model. A case study of a hydro-wind-solar base in Southwest China demonstrates that the proposed model can effectively leverage the regulation ability of hydropower to coordinate multiple power sources with the restrictions of multistage transmission sections, effectively alleviating the congestion of transmission channels and reducing the curtailment of renewable energy.

Automatic interval management for aircraft based on dynamic fuzzy speed control considering uncertainty

A novel real-time autonomous Interval Management System (IMS) is proposed to automate interval management, which considers the effect of wind uncertainty using the Dynamic Fuzzy Velocity Decision (DFVD) algorithm. The membership function can be generated dynamically based on the True Air Speed (TAS) limitation changes in real time and the interval criterion of the adjacent aircraft, and combined with human cognition to formulate fuzzy rules for speed adjusting decision-making. Three groups of experiments were conducted during the en-route descent stage to validate the proposed IMS and DFVD performances, and to analyze the impact factors of the algorithm. The verification experimental results show that compared with actual flight status data under controllers’ command, the IMS reduces the descent time by approaching 30% with favorable wind uncertainty suppression performance. Sensitivity analysis shows that the ability improvement of DFVD is mainly affected by the boundary value of the membership function. Additionally, the dynamic generation of the velocity membership function has greater advantages than the static method in terms of safety and stability. Through the analysis of influencing factors, we found that the interval criterion and aircraft category have no significant effect on the capability of IMS. In a higher initial altitude scenario, the initial interval should be appropriately increased to enhance safety and efficiency during the descent process. This prototype system could evolve into a real-time Flight-deck Interval Management (FIM) tool in the future.

Benefit of wind networking for aircraft arrival scheduling in terminal manoeuvring area

The effectiveness of air traffic management depends on the amount of obtained information and the accuracy of prediction, leading to a reduction in uncertainty disturbances, and an improvement in the robustness of decision-making results. Among all controlled areas, the Terminal Manoeuvring Area (TMA) is a complex and sophisticated airspace surrounding a coordinated airport in which there exists a high density of traffic, especially with arrivals converging from different directions. With the purpose of improving safety levels and operational efficiency, this paper addresses the aircraft arrival scheduling problem at the microscopic level, integrating the meteorological uncertainty based on wind networking into the optimization model. Wind uncertainty affects the flight speed, which in turn leads to uncertainty in the flight arrival time at one waypoint. Conflict detection and resolution are performed at waypoints and links in a predefined network, based on the predicted time information from the designated route. In order to optimize the time and speed for each aircraft entering TMA, this paper proposes a mathematical model that seeks to minimize the number of potential conflicts, flight delays and the number of flights deviating from the original plan under two assumptions. The first one considers regular weather forecasts for predicting the future positions of aircraft for conflict detection. The second one investigates the potential benefit for aircraft to share their local wind measure thanks to the ADSB-IN and ADSB-OUT channels. A resolution approach is proposed combining a simulated annealing algorithm and a simulation framework. Using data from a case study with 437 flights overflying the Paris Charles de Gaulle (CDG) airport TMA, we demonstrate the validity of the proposed scheduling strategy. A performance analysis is then conducted between standard forecast and wind networking.

Aggregation and Scheduling of Multi-Chiller HVAC Systems in Continuous-Time Stochastic Unit Commitment for Flexibility Enhancement

Buildings, with their heating, ventilation, and air conditioning (HVAC) systems are the promising demand side resources for power grid to cope with the wind uncertainty. The challenge, however, is to ensure an efficient incorporation of large scale of HVACs into unit commitment to enhance the intrahour flexibility for system operation. To this end, this paper focuses on the aggregation and scheduling of multi-chiller HVAC systems in continuous-time stochastic unit commitment. The continuous-time modeling method is utilized to handle the subhourly variability of wind power and the intra-hour flexibility of the HVAC systems. To describe the electricity consumption characteristic of the HVAC system with multiple chillers, a cooling model is formulated based on the chiller load sharing strategy and linearization method. Besides, an aggregation method for heterogeneous HVACs to provide reserve capacity is proposed to improve computational efficiency. Simulation results on the modified IEEE 118-test systems validate the effectiveness of the modeling and aggregation for multi-chiller HVAC systems, and demonstrate the benefits of applying the continuous-time HVAC reserve provision model to enhance the flexibility for the power system operation.

Stochastic Multi-Objective Optimal Reactive Power Dispatch with the Integration of Wind and Solar Generation

The exponential growth of unpredictable renewable power production sources in the power grid results in difficult-to-regulate reactive power. The ultimate goal of optimal reactive power dispatch (ORPD) is to find the optimal voltage level of all the generators, the transformer tap ratio, and the MVAR injection of shunt VAR compensators (SVC). More realistically, the ORPD problem is a nonlinear multi-objective optimization problem. Therefore, in this paper, the multi-objective ORPD problem is formulated and solved considering the simultaneous minimization of the active power loss, voltage deviation, emission, and the operating cost of renewable and thermal generators. Usually, renewable power generators such as wind and solar are uncertain; therefore, Weibull and lognormal probability distribution functions are considered to model wind and solar power, respectively. Due to the unavailability and uncertainty of wind and solar power, appropriate PDFs have been used to generate 1000 scenarios with the help of Monte Carlo simulation techniques. Practically, it is not possible to solve the problem considering all the scenarios. Therefore, the scenario reduction technique based on the distance metric is applied to select the 24 representative scenarios to reduce the size of the problem. Moreover, the efficient non-dominated sorting genetic algorithm II-based bidirectional co-evolutionary algorithm (BiCo), along with the constraint domination principle, is adopted to solve the multi-objective ORPD problem. Furthermore, a modified IEEE standard 30-bus system is employed to show the performance and superiority of the proposed algorithm. Simulation results indicate that the proposed algorithm finds uniformly distributed and near-global final non-dominated solutions compared to the recently available state-of-the-art multi-objective algorithms in the literature.

Peak shaving and short-term economic operation of hydro-wind-PV hybrid system considering the uncertainty of wind and PV power

With uncertain wind and PV power integrated into the grid, the difficulty of peak shaving is exacerbated. Therefore, the peak shaving operation of hydropower has become one of the most important problems in power system. In this paper, an optimal operation strategy of hydro-unit level coordinated peak shaving and economic operation in hydro-wind-PV hybrid system under uncertain conditions of wind and PV power is proposed. Firstly, the uncertainty of wind and PV power is described based on Latin hypercube sampling and scenario reduction methods. Secondly, a two-layer optimization model considering wind and PV uncertainty is established. And then, the synchronous peak shaving strategy and the improved lambda flow iteration strategy are proposed to solve the model. A case study is performed with the HWPHS in the Yarlung Zangbo River basin of China. The results show that (1) The residual load of power system fluctuates steadily under the condition of wind and PV uncertainty, and the peak shaving rate is 95.53%. (2) Compared with the DP algorithm, the proposed algorithm can increase the economic efficiency by 0.89% when solving the lower-layer model. (3) The V3 shaped mapping function proved to be superior to other functions.

Combining monthly wind and inflow uncertainties in the stochastic dual dynamic programming

AbstractFollowing a global trend, intermittent sources, especially wind, have been experiencing accelerated growth in Brazil—in the last decade, wind power grew 13 times and became the second largest source in the electricity mix (12%), just behind hydropower (60%). Currently, although following regulatory guidelines, the representation of wind power in the long-term operation planning model is done in a simplified way, based on the monthly average of the last five years of aggregated generation, thus demanding improvements. The objective of this work is to describe an approach to be used by the Brazilian power industry to represent the uncertainties of monthly wind power production in the SDDP algorithm applied in the long-term operation planning model, keeping the large-scale stochastic problem still computationally viable, when applied to large interconnected systems, especially with hydroelectric predominance. The proposed methodology comprises statistical clustering of wind regimes and definition of equivalent wind farms; evaluation of monthly transfer functions between wind speed and power production; integrated generation of monthly multivariate synthetic scenarios of inflows and winds, considering associated cross-correlations; and representing monthly wind power in the SDDP algorithm. The application to real configurations of the Brazilian interconnected system, including case studies related to the monthly operation program and the calculation of the maximum amount of energy that can be traded in long-term power purchase agreements, points to its effectiveness and the relevance of modeling the wind uncertainties in the long-term operation planning of large hydro-dominated systems.

Blockchain-Based Decentralized Power Dispatching Model for Power Grids Integrated with Renewable Energy and Flexible Load

To cope with the energy crisis and environmental pollution, the future development of the power system has to change towards a clean, low-carbon, flexible, and diversified direction. This paper proposes a decentralized power dispatching model based on blockchain technology to address the problems of uncertainty, privacy, security, and reliability in power dispatching systems containing renewable energy and flexible loads. Considering the uncertainty of wind, photovoltaic, and flexible load integration into the power grid, the total generation costs of the system are established, and the smart contracts of the decentralized power dispatching are proposed. The proof of work (PoW) consensus mechanism is improved in this paper. The hash operation that must be repeated in the PoW algorithm is replaced by an optimized computation process using a blockchain-based genetic algorithm (BD-GA). The proof of work-load-genetic algorithm-based (PoW-GAD) consensus algorithm is proposed. The decentralized power dispatching model and improved consensus algorithms’ effectiveness was confirmed by simulation. The power dispatching method in this paper reduces the system cost and increases wind and photovoltaic usage. The improved PoW-GAD algorithm, while inheriting the security features of the PoW algorithm, adapts to the blockchain-based decentralized dispatching structure and enhances system security.

Probabilistic Optimal Active and Reactive Power Dispatch including Load and Wind Uncertainties considering Correlation

The increased integration of renewable energies (REs) raised the uncertainties of power systems and has changed the approach to dealing with power system challenges. Hence, the uncertain nature of all the power system variables needs to be considered while dealing with the optimal planning and operation of modern power systems. This paper presents a probabilistic optimal active and reactive power dispatch (POARPD) based on the point estimate method (PEM), considering the uncertainties associated with load variation and wind power generation. In the POARPD, the deterministic optimal active and reactive power dispatch (OARPD) is performed in two stages, which gives a deterministic two-stage OARPD (TSOARPD). The objectives of TSOARPD are the operating cost (OC) minimization in stage 1 and voltage stability (VS) maximization in stage 2, whereas the VS is improved by maximizing the system’s reactive power reserve (RPR). In this paper, instead of using multiobjective optimal power flow, this TSOARPD is used to give more importance to VS when the system is substantially loaded. The POARPD problem is solved using PEM for modified IEEE-9 bus and standard IEEE-30 bus test systems by considering the correlation between the loads. The results are compared with Monte Carlo simulation (MCS). While solving POARPD, the voltage-dependent load model is used to account for the real-time voltage dependency of power system loads. This paper discusses the detailed procedure of solving POARPD by considering correlation and the increased nonlinearities by giving more importance to VS when the system is heavily loaded.

Estimation of the wind drift factor and uncertainty analysis based on CFD computer simulations

PurposeThe purpose of this work is to present a procedure for determining the wind drift factor through two-dimensional computational fluid dynamics (CFD) simulations of the wind acting on a wavy sea surface, such that the subjectivity of its estimation is reduced.Design/methodology/approachThe wind drift factor was determined by two-dimensional CFD analyses with open-channel condition. The characteristic wave was determined by the Sverdrup–Munk–Bretschneider (SMB) method. The uncertainty analysis is based on convergence studies using a single parameter refinement (grid and time step).FindingsThis procedure allows the estimation of the wind drift factor in a fetch-limited domain. The domain's value in the analyzed region is 0.0519 ± 4.92% which is consistent with the upper values of the wind drift factors reported in the literature.Research limitations/implicationsThe use of a three-dimensional domain was impractical with the available computational resources because of the fine mesh required for wave modeling. The uncertainty analysis consisted only of a verification procedure. Validation against real data was not possible because of the lack of measured data in the analyzed region.Originality/valueThe wind drift factor is usually estimated based on either experience or random sampling. The original contribution of this work is the presentation of a CFD procedure for estimating the wind drift factor, in which the domain inlet is subjected to a wave boundary condition and to a wind velocity.

Optimization of integrated load dispatch in multi-fueled renewable rich power systems using fractal firefly algorithm

This manuscript applied fractal firefly optimization technique to the integrated load dispatch (ILD) problem involving loads allocation to power generating units with the minimum total fuel cost and emissions while handling the constraints for large-scale multi-fueled power plants and integration of stochastic wind to provide sustainable energy. The penetration of wind energy into conventional grids has resolved power system scheduling issues at the cost of rise in the stiffness of nonconvex ILD optimization problem. In order to enhance the dispatch performance with significant penetration of wind energy, an effective framework of fractal heritage is introduced inspired by Firefly algorithm. In order to validate the efficacy and flexibility of the proposed algorithm, sundry non-convex ILD optimization scenarios with valve-point effects, capacity constraints, multi-fuels power plants and Weibull's distributed stochastic wind uncertainty is implemented. The results reveal stupendous performance in term of the minimum fuel cost with higher efficiency and finer convergence rate than that of conventional algorithms.

A multi-energy multi-microgrid system planning model for decarbonisation and decontamination of isolated systems

Decarbonising and decontaminating remote regions in the world presents several challenges. Many of these regions feature isolation, dispersed demand in large areas, and a lack of economic resources that impede the development of robust and sustainable networks. Furthermore, isolated systems in the developing world are mostly based on diesel generation for electricity, and firewood and liquefied petroleum gas for heating, as these options do not require a significant infrastructure cost. In this context, we present a stochastic multi-energy multi-microgrid system planning model that integrates electricity, heat and hydrogen networks in isolated systems. The model is stochastic to capture uncertainty in renewable generation outputs, particularly hydro and wind, and thus design a multi-energy system proved secured against such uncertainty. The model also features two distinct constraints to limit the emissions of CO2 (for decarbonisation) and particulate matter (for decontamination), and incorporates firewood as a heating source. Moreover, given that the focus is on low-voltage networks, we introduce a fully linear AC power flow equations set, allowing the planning model to remain tractable. The model is applied to a real-world case study to design a multi-energy multi-microgrid system in an isolated region in Chilean Patagonia. In a case with a zero limit over direct CO2 emissions, the total system’s cost increases by 34% with respect to an unconstrained case. In a case with a zero limit over particulate matter emissions, the total system’s cost increases by 189%. Finally, although an absolute zero limit over both, particulate matter and direct CO2 emissions, leads to a total system’s cost increase of 650%, important benefits in terms of decarbonisation and decontamination can be achieved at marginal cost increments.

A multi-objective optimization model for the coordinated operation of hydropower and renewable energy

The rapid growth of wind and solar energy sources in recent years has brought challenges to power systems. One challenge is surging wind and solar electric generation, understanding how to consume such generation is important. Achieving the complementarity of hydropower and renewable energies such as wind and solar power by utilizing the flexible regulation performance of hydropower is helpful to provide firm power to help renewable energy consumption. However, the multi-energy complementary operation mode will change the traditional hydropower operation mode, causing challenges to the comprehensive utilization of hydropower. In this paper, a multi-objective optimal scheduling model is built by considering coordinated hydro-wind-solar system peak shaving and downstream navigation. First, the Gaussian mixture model is adopted to quantify the uncertainty of wind and solar power. Then, a hydro-wind-solar coordinated model was built to obtain the standard deviation of the residual load and the standard deviation of the downstream water level. Finally, the ε-constraint method is used to solve for the Pareto optimality. The results demonstrate the following: 1) The proposed model can effectively determine hydropower output schemes that can coordinate wind and solar power output to reconcile peak shaving and navigation; 2) The downstream hydropower stations’ reverse regulation of the upstream hydropower station is a positive factor in reconciling conflicts; and 3) Reasonable planning of wind power and solar power is helpful for hydro-wind solar power complement operation.

Multi-objective two-stage stochastic unit commitment model for wind-integrated power systems: A compromise programming approach

In this paper, we introduce a compromise programming (CP) framework for solving a multi-objective two-stage stochastic unit commitment problem characterized by high penetration of wind power. The proposed framework aims at finding best-compromise Pareto efficient on/off schedules, accounting for wind and power demand uncertainties: such solutions must trade off the three objectives of operating cost, CO2 emissions, and wind power curtailment in accordance to the decision maker preferences. To achieve this, we introduce a practical procedure to compute the ideal and Nadir points associated to the multi-objective two-stage stochastic unit commitment problem and propose a linearized ℓ1 norm-based compromise program to design best-compromise on/off schedules that correspondingly minimize and maximize their weighted distances to the ideal point and to the Nadir point, considering the preference weights assigned by the decision maker to each of the three objective functions. The proposed CP framework is applied to a case study related to the New England IEEE-39 bus test system. The results show that, compared to the schedule obtained through the traditional minimization of operating cost, the designed best-compromised schedules considerably improve CO2 emissions reduction and wind power curtailment performance by conservatively sacrificing operating cost performance.

Two-timescale coordinated operation of wind-advanced adiabatic compressed air energy storage system: A bilevel stochastic dynamic programming method

Renewable energy is a promising solution to address the energy crisis and environmental issues, but it comes with challenges due to its inherent volatility and limited dispatchability. Advanced adiabatic compressed air energy storage (AA-CAES) is a favorable partner for centralized renewable integration, due to its numerous benefits, such as large capacity, long lifetime, fast response capability, and zero carbon emissions. For the economic management of a wind-AACAES system, a battery-like AA-CAES dispatch model is proposed, where the charging/discharging efficiencies and capacities are dependent on the operating power and state-of-charge (SoC) to capture the part-load characteristics. A hybrid control strategy is proposed to enhance the flexibility and efficiency of the compression side under off-design conditions caused by simultaneous changes in back pressure and load. To provide dispatch and control strategies of AA-CAES, a multi-timescale optimization problem is established. The slow timescale determines the baseline output scheduling on an hourly basis to maximize total revenue, while the fast timescale updates the real-time adjustment every five minutes to minimize the penalty of tracking error. A bi-level stochastic dynamic programming (SDP) framework is formulated to incorporate the wind uncertainties and multi timescale coordination, where terminal SoCs and value functions are essential to integrate decisions across slow and fast timescales. A non-iterative parametric programming-based method is proposed to solve the slow-timescale SDP, and a simulation-based rollout algorithm is applied to extract the fast-timescale actions, which yields evident improvement over any heuristic base policy that is sequentially consistent. The numerical results demonstrate that the proposed method has a performance gap of approximately 7.1%, which outperforms the rule-based method by 32.6%. The installation of AA-CAES improves the total revenue by 11.9%. Additionally, the hybrid control strategy enhances the charging flexibility and efficiency by 30.7% and 4.3%, respectively, resulting in a 3.9% reduction in tracking deviation penalty.

Stochastic scheduling of power system in the presence of electric vehicle and renewable sources considering security and economic indexes using an improved mutation particle swarm optimization (M-PSO) algorithm

Increased air pollution and global temperature as well as motor vehicle fuel consumption have depleted fossil fuel resources and increased environmental problems caused by the consumption of such fuels. In addition to methods such as combined heat and power (CHP) technology and distributed generation (DG) of energy at the consumption site, renewable energy sources and EVs are considered suitable methods for achieving this goal, which is prepared by the grid or battery electric energy. Generation uncertainty due to the lack of solar radiation and constant wind blow at different hours of the day is the only challenge for using renewable energies. Moreover, system reliability is a concept that refers to the safe and reliable operation of the system. In general, the wider and more important the system, the more attention that is paid to calculating its reliability in planning and decision making. This study aims to examine the problem of probabilistic power system planning by calculating the power system reliability, evaluating the effect of the presence of these vehicles on security and economic indicators and renewable energy sources, and modeling uncertainties using a Least Squares Generative Adversarial Network (LSGANs) method with generating various scenarios for solar irradiance and wind speed. Furthermore, the Kantorovich distance matrix (KDM) is used to reduce the number of generated scenarios. In the proposed model, the conditional value-at-risk (CVaR) method is implemented to assess and control the risk caused by uncertainties of the proposed problem. Using the power stored in the EV battery is evaluated to cover wind and solar energy source uncertainties.

Reinforcement learning-based composite differential evolution for integrated demand response scheme in industrial microgrids

The fourth industrial revolution is being propelled by the “Energy Internet,” which aims to encourage the integration of industrial multi-energy microgrids (MEMG) and renewable energy sources. The conventional demand response (DR) schemes only utilize a single energy source, which limits the industrial users (IUs) and prevents them from making full use of the demand side's communication capabilities. However, smart industrial multi-energy microgrids (MEMGs) give IUs additional options for meeting their energy needs by integrating diverse energy sources, including electricity, natural gas, and thermal power. This new approach to DR programs is known as “Integrated Demand Response” (IDR). This research work proposes a smart IDR program for a novel grid-connected industrial MEMG framework consisting of exhaust air wind turbines, concentrated photovoltaic-thermal panels, an electrical energy storage system (EES), a thermal energy storage (TES), a diesel generator, an indirect customer-to-customer energy trading platform, and typical electrical and thermal industrial loads. The proposed smart IDR considers the uncertainties of both wind and solar power generation and the buying and selling costs of electrical and thermal energy to automatically reduce the industry's total power consumption and battery EES degradation costs. A novel State-Action-Reward-State-Action (SARSA)-based composite different evolution (DE) method is proposed to solve a complex scenario-based non-convex optimization problem. It uses two selection strategies, three mutation strategies, and a positive feedback mechanism to change the states of the individuals. The strategies are coupled in pairs, resulting in a total of six distinct actions that may be performed by the SARSA agents. This allows an individual to not get stuck at a local optimum and adaptively benefit from all the mutation and parameter selection methods. Moreover, SARSA has introduced two more factors, the discount factor and the learning rate, which further improve the optimization performance. The proposed method is also compared with five other state-of-the-art methods to prove its effectiveness in minimizing industrial energy bills and battery degradation costs. The simulated results confirmed that the proposed SARSA-based composite DE algorithm has achieved the lowest total energy cost and battery degradation costs when compared with other state-of-the-art algorithms.