Electricity Market Participants Research Articles

Synergistic Integration of EVs and Renewable DGs in Distribution Micro-Grids

This paper proposes a multi-objective optimization framework for safe, reliable, and economic integration of electric vehicles (EVs) and renewable distributed generators (DGs) in distribution micro-grids. EV and DG coordination optimization with the use of vehicle-to-grid (V2G) technology along with system reconfiguration optimization is developed to provide collective revenues and address integrational complications that may occur by additional system loading due to EV charging and EV-DG energy exchanges. A Genetic Algorithm (GA) optimizes the EV charging/discharging in synergies with renewable DGs to maximize benefits that can be captured by their collaborative participation in electricity market and through renewable energy arbitrage. The developed EV charging/discharging optimization is implemented in a real 134-bus distribution network and is evaluated for its potential operational implications, namely, increased system losses. A system reconfiguration is then proposed to reduce the system losses by optimizing the flow of power through switching on/off the connections within the micro-grid and/or with other distribution systems. Simulation results demonstrate the efficiency of the proposed method in not only providing collective revenues, but also in enhancing the system operation by reducing the losses of the distribution grid. The collective benefits proposed by the developed optimization and validated by the simulation results facilitate transitioning to clean and eco-friendly sources of energy for generation and transportation, which in turn leads to more sustainable development of societies and communities.

Metaheuristic optimization algorithms comparison adopted for the profit maximization of electricity market participants

The electricity market faces numerous challenges due to the growing demand for energy, increasing penetration of renewable energy sources, and the need for grid reliability and efficiency. To address these challenges, optimization algorithms have emerged as essential tools for optimizing various aspects of the electricity market, including generation, transmission, distribution, and demand-side management. The review can be done by providing an overview of the key components and challenges of the electricity market, including generation dispatch, unit commitment, economic dispatch, transmission network optimization, and demand response management. It then systematically examines a wide range of optimization techniques employed in addressing these challenges, including linear programming, mixed-integer linear programming, nonlinear programming, dynamic programming, genetic algorithms, particle swarm optimization, simulated annealing, and machine learning-based approaches. This paper presents a comparison of optimization algorithms, RCEDUMDA (Ring-Cellular Encode-Decode Univariate Marginal Distribution Algorithm) and CL_HC2RCEDUMDA (Hill Climbing to Ring Cellular Encode-Decode Univariate Marginal Distribution Algorithm) for the profit maximization of Electricity Market consumers & prosumers.

Metaheuristic Optimization Algorithms Comparison Adopted for the Profit Maximization of Electricity Market Participants

The electricity market faces numerous challenges due to the growing demand for energy, increasing penetration of renewable energy sources, and the need for grid reliability and efficiency. To address these challenges, optimization algorithms have emerged as essential tools for optimizing various aspects of the electricity market, including generation, transmission, distribution, and demand-side management. The review can be done by providing an overview of the key components and challenges of the electricity market, including generation dispatch, unit commitment, economic dispatch, transmission network optimization, and demand response management. It then systematically examines a wide range of optimization techniques employed in addressing these challenges, including linear programming, mixed-integer linear programming, nonlinear programming, dynamic programming, genetic algorithms, particle swarm optimization, simulated annealing, and machine learning-based approaches. This paper presents a comparison of optimization algorithms, RCEDUMDA (Ring-Cellular Encode-Decode Univariate Marginal Distribution Algorithm) and CL_HC2RCEDUMDA (Hill Climbing to Ring Cellular Encode-Decode Univariate Marginal Distribution Algorithm) for the profit maximization of Electricity Market consumers & prosumers.

Визначення граничних величин споживання електричної енергії засобами оптимізаційного моделювання

In the heating season of 2022/2023, as a result of the military aggression of the Russian Federation and targeted attacks on electric power facilities, a significant shortage of electric energy occurred in the Integrated power system of Ukraine. Restriction schedules and emergency disconnection of consumers were forcibly applied. In the conditions of such an unprecedented violation of the security of electricity supply, the problem of determining the limit values of electric energy and power consumption has gained new relevance for the electricity market participants. In this study, the problem of determining the optimal limit values of electricity consumption based on the criterion of maximum income from its sale to three groups of consumers was set and solved: "Critical infrastructure", "Households" and "Non-household consumers". The formation of the three specified groups is related to price discrimination in the electricity market and the need to supply critical infrastructure facilities without limits. The decision variables in the optimization model are proposed to be specified in fractions of the provision of electrical energy needs (unit fractions), which allows for establishing equal conditions regarding restrictions for all distribution system operators. To take into account the social significance of electric energy as a commodity, an additional constraint was included to the basic optimization model: the lower limit of the decision variable for the "Households" group. Approbation of the proposed optimization model was carried out using spreadsheet modeling in MS Excel on reported data on the results of electrical load measurements on regime days. The results of computational experiments are presented for the conditions of different values of the deficit of electric energy in the Integrated power system of Ukraine and different values of the additional constraint for the «Households» group, in particular, quantitative estimates of the consequences of the included constraints for the functioning of the electricity market. The proposed method of determining the limit values of electric energy consumption allows to formalize the procedure for decision-making according to predetermined rules and thereby achieve a fair distribution of limited resources. Keywords: electric energy consumption, shortage, limit value, optimization modelling, spreadsheet model.

Research on the operation strategy of joint wind-photovoltaic-hydropower-pumped storage participation in electricity market based on Nash negotiation

Under the research background of China vigorously promoting the planning and construction of multi-energy complementary energy bases as well as the steady advancement of the electricity market, how to better promote the participation of large-scale multi-energy complementary bases in the electricity market has become a new research focus. In this paper, a joint optimization model for the participation of multi-energy systems in the electric energy market and auxiliary service market is proposed based on the Nash negotiation theory with coordinated wind-photovoltaic-pumped-storage-hydropower (WPPSH) generation systems as the research objects. Further, the joint optimization model is equated into two subproblems, namely, maximizing the net return of the alliance and negotiating the payment of the multi-energy complementary transaction, and the alternating direction method of multiplier algorithm (ADMM) is used to solve the above two subproblems separately. The simulation results show that the revenue of WPPSH increased by 25.82%, 30.67%, 49.35% and 3.78% respectively after joint operation, and the absorption rates of wind power (WD), photovoltaic (PV) and hydropower (HY) increased by 17.69%, 21.87% and 9.01% respectively. Through the cooperation of WPPSH generation systems, the income of each entity and the alliance can be improved, the fair distribution of incremental income is basically realized, and the consumption of clean energy can be promoted. In addition, the capacity allocation cap ratio of pumped storage (PS) units in the energy market and auxiliary service market will have a certain impact on the returns of WPPSH generation systems in multi-principal cooperation.

Analysis of Risk Characterization and Identification Techniques for Electricity Spot Settlement Based on Multilayer Perceptron Machine

Abstract In this paper, the structural characteristics of the perceptron neural network and the calculation method of the hierarchical relationship of the MLP neural network model are first studied. Then the aspects of two-part settlement, generation-side settlement, and customer-side settlement in the electricity spot settlement mechanism are studied, and the importance of these mechanisms for the operation of the electricity market and risk identification is pointed out. Following that, the effectiveness of the risk identification model is assessed and analyzed. This paper examines market performance indicators, the impact of the dual-track mechanism, and the time characteristics of the price index to characterize risk. The results show that in Guangdong, for example, the price in the day-ahead market is much higher than the supply-demand equilibrium price most of the time, and the maximum difference can be as high as 0.662 yuan/(kW-h). For the entire month, the real-time market’s average price is RMB 0.546/(kW-h) and it is RMB 0.063/(kW-h) higher than the day-ahead market. The importance of this study lies in its role in managing and responding to risks for electricity market operators and participants.

Techno-Economic Analysis of a Highly Renewable and Electrified District Heating Network Operating in the Balancing Markets

In pursuit of Finland’s carbon neutrality objective by 2035, integrating renewable energy sources into the power grid is essential. To address the stochastic nature of these resources, additional sources of flexibility are required to maintain grid stability. Meanwhile, district heating network (DHN) operators in Finland are decommissioning fossil fuel-based combined heat and power plants (CHPs) and electrifying heating systems with heat pumps (HPs) and electric boilers. A techno-economic assessment and the optimized operation of DHN-connected HPs and electric boilers in providing ancillary balancing services were explored in this study. The primary goal was to maximize the potential revenue for DHN operators through participation in the day-ahead electricity market and frequency containment reserve (FCR) balancing markets. Three interconnected DHNs in the Helsinki metropolitan area were optimized based on 2019 data and each operator’s decarbonization strategies for 2025. HPs are expected to achieve the highest profit margins in the FCR-D up-regulation market, while electric boilers could generate substantial profits from the FCR-D down-regulation market. In contrast to other balancing markets studied, the FCR-N market exhibited limited profit potential. Sensitivity analysis indicated that spot electricity prices and CO2 emission allowance prices significantly influence the profitability derived from balancing markets.

RETRACTED:Optimum planning of energy hub with participation in electricity market and heat markets and application of integrated load response program with improved particle swarm algorithm

The drive for improved energy efficiency and flexibility has birthed an innovative solution: an energy hub. This hub operates in sync with natural gas and electricity grids, integrating batteries and thermal storage to optimize renewable energy use, reduce costs, and bolster network stability. In addressing these objectives, a mathematical optimization model for energy hub operation is developed in this paper. This model captures the intricate interplays between electricity and natural gas networks, accounting for the intricacies posed by uncertainties and variations in renewable energy sources and demand profiles. Also, this paper uniquely delves into the integration of load response programs, an approach geared towards amplifying the energy hub system's flexibility and reliability. Through these programs, subscribers gain the agency to calibrate their energy consumption based on real-time pricing signals and incentives dispensed by the energy hub. The simulation findings serve as a compelling testament to the efficacy of the proposed system. Operating costs witness a substantial reduction, the adoption of renewable energy sources is markedly heightened, and the stability and reliability of the upstream energy networks are tangibly ameliorated. The integration of load response programs emerges as a particularly effective strategy in mitigating peak demand and augmenting the system's overall energy efficiency. Underpinning the entirety of this innovative solution is the transformation of the challenges into an optimization problem. This catalyzes the employment of a newly developed particle community algorithm, custom-tailored to surmount the challenges of local optima. This algorithm inherently bolsters the system's search capabilities, minimizing the risk of entrapment within localized solutions. Ultimately, the proposed energy hub system encapsulates a promising trajectory toward the realization of a sustainable and adaptable energy landscape. By seamlessly integrating diverse energy sources and storage systems, augmenting energy flexibility and efficiency, and aligning with broader energy transition and decarbonization goals, this solution presents a formidable contender. The simulation outcomes underscore its potential by showcasing a substantial 4.57 % reduction in the cost of procuring energy from the upstream electrical network.

An Optimized Decision Model for Electric Vehicle Aggregator Participation in the Electricity Market Based on the Stackelberg Game

With the growing popularity of charging pile infrastructure and the development of smart electronic devices and 5G communication technologies, the electric vehicle aggregator (EVA) as a bidding entity can aggregate numerous electric vehicle (EV) resources to participate in the electricity market. Moreover, as the number of grid-connected EVs increases, EVA will have an impact on the nodal marginal prices of electricity market clearing. Aiming at the bidding and offering problem of EVA participation in the day-ahead and intra-day electricity markets, based on the Stackelberg game theory, this paper establishes a bilevel optimization model for EVA participation in the two-stage electricity market as a price-maker. In the proposed bilevel model, the upper-level and lower-level models are constructed as an operational problem for EVA and a market-clearing problem for independent system operator (ISO), respectively. In the day-ahead stage, EVA is optimized to maximize its own expected benefits, and ISO aims to improve the social benefits. In the intra-day stage, EVA is optimized to maximize its self-interest, and the ISO aims to make it possible to minimize the cost of expenditures to maintain the system’s supply–demand balance. Karush–Kuhn–Tucker (KKT) conditions and dual theory are used to transform the nonlinear bilevel programming model into a mixed-integer single-level linear programming model. In order to verify the validity of the proposed bilevel model as well as to comparatively analyze the impact of EVA’s participation in the electricity market on the market clearing results. Two scenarios are set up where EVA is seen as the price-taker in Scenario 1 and EVA is seen as the price-maker in Scenario 2. ISO’s revenue under Scenario 2 increased by USD 2262.66 compared to Scenario 1. In addition, the EVA acts as an energy consumer in Scenario 1 with a charging cost of USD 26,432.95, whereas in Scenario 2, the EVA can profit by participating in the electricity market with a revenue of USD 26,432.95, at which point the EVA acts like a virtual power plant. The simulation examples verify that the proposed bilevel optimization model can improve the benefits of ISO and EVA at the same time, achieving mutual benefits for both parties. In addition, the simulation analyzes the impact of abandonment penalty price on ISO and EVA intra-day revenues. Comparing the scenarios where the abandonment penalty price is 0 with USD 10/MW, the ISO’s revenue in the intra-day market decreases by USD 197.5. Correspondingly, EVA’s reserve capacity is dispatched to consume wind power in the intra-day market, and its revenue increases by USD 197.5. The proposed two-stage bilevel optimization model can provide a reference for EVA to develop scheduling strategies in the day-ahead and intra-day electricity markets.

A New Multi-Resolution Closed-Loop Wind Power Forecasting Method

By the increasing number and size of wind farms, wind generation forecasting has become a basic requirement for their connection to the power grid; otherwise, power system operators and electricity market participants cannot make the right decisions and may incur significant costs and penalties. In this paper, a new multi-resolution closed-loop wind power forecasting method with a difference signal feedback loop is proposed. Within the proposed method, wind power is initially predicted in two different resolutions (such as with hourly and sub-hourly time steps) by two low/high-resolution pre-predictors and then the inconsistency between their predictions is measured through the difference signal. The generated difference signal is used as a guide for the two low/high-resolution wind power post-predictors. If their wind power forecasts are inconsistent, the difference signal is updated and used as the feedback for the low/high-resolution post-predictors. This closed-loop forecasting-updating process is iterated until the post-predictors reach consistent results. To evaluate the performance of the proposed multi-resolution closed-loop method, it is tested on two different real-world wind farms and the results are compared with the results of several other widely used/recently published wind power forecast methods using various error metrics and different forecast horizons.

Hierarchical model predictive control for islanded and grid-connected microgrids with wind generation and hydrogen energy storage systems

This paper presents a novel energy management strategy (EMS) to control a wind-hydrogen microgrid which includes a wind turbine paired with a hydrogen-based energy storage system (HESS), i.e., hydrogen production, storage and re-electrification facilities, and a local load. This complies with the mini-grid use case as per the IEA-HIA Task 24 Final Report, where three different use cases and configurations of wind farms paired with HESS are proposed in order to promote the integration of wind energy into the grid. Hydrogen production surpluses by wind generation are stored and used to provide a demand-side management solution for energy supply to the local and contractual loads, both in the grid-islanded and connected modes, with corresponding different control objectives. The EMS is based on a hierarchical model predictive control (MPC) in which long-term and short-term operations are addressed. The long-term operations are managed by a high-level MPC, in which power production by wind generation and load demand forecasts are considered in combination with day-ahead market participation. Accordingly, the hydrogen production and re-electrification are scheduled so as to jointly track the load demand, maximize the revenue through electricity market participation and minimize the HESS operating costs. Instead, the management of the short-term operations is entrusted to a low-level MPC, which compensates for any deviations of the actual conditions from the forecasts and refines the power production so as to address the real-time market participation and the short time-scale equipment dynamics and constraints. Both levels also take into account operation requirements and devices’ operating ranges through appropriate constraints. The mathematical modeling relies on the mixed-logic dynamic (MLD) framework so that the various logic states and corresponding continuous dynamics of the HESS are considered. This results in a mixed-integer linear program which is solved numerically. The effectiveness of the controller is analyzed by simulations which are carried out using wind forecasts and spot prices of a wind farm in center-south of Italy.

Demand response scheduling of copper production under short-term electricity price uncertainty

Marketing demand response of industrial processes on electricity spot markets can reduce operational cost. We apply our simultaneous day-ahead and intraday electricity market participation approach (Germscheid et al., AIChE J. 2022;68:e17828) to analyze the demand response potential of power-intensive copper production with our previously derived resource–task network model (Röben et al., J. CLEAN. PROD. 2022;362:132221). Specifically, we tackle intraday price uncertainty by stochastic scheduling optimization considering both risk-neutral and risk-averse market participation. Risk-averse participation allows for 1.9% weekly savings compared to only participating on the day-ahead market. Risk-neutral participation allows for 6.4% savings, but is connected to higher financial risks on weekends. Moreover, we show that load-shifting capabilities significantly depend on modeling on/off decisions either as first or second-stage integer decisions and that sequential day-ahead and intraday scheduling allows to participate in both markets while balancing financial risk, expected cost, and computational complexity compared to stochastic scheduling.

A new framework for electricity price forecasting via multi-head self-attention and CNN-based techniques in the competitive electricity market

Due to recent technical improvements, the smart grid has become a feasible platform for electricity market participants to successfully regulate their bidding process based on demand-side management (DSM) perspectives. At this level, practical design, implementation, and assessment of numerous demand response mechanisms and robust short-term price forecasting development in day-ahead transactions are all critical. The accuracy and effectiveness of the day-ahead price forecasting process are crucial concerns in a deregulated market. In this market, the reason for low accuracy is the limitation of electricity generation compared to the electricity demand variations. Hence, this study proposes a suitable technique for forecasting electricity prices using a multi-head self-attention and Convolutional Neural networks (CNN) based approach. Further, this study develops a feature selection technique using mutual information (MI) and neural networks (NN) to choose suitable input variable subsets significantly affecting electricity price predictions simultaneously. The combination of MI and NN reduces the number of input features used in the model, thereby decreasing the computational complexity of the NN. The actual data sets from the Ontario electricity market in 2020 are acquired to verify the simulation results. Finally, the simulation results proved the efficiency of the proposed method by demonstrating increased accuracy by attaining the lowest average value for MAPE and RMSE with a value of 1.75% and 0.0085, respectively, and compared to results obtained by recent computational intelligence approaches. By attaining accurate electricity price results, the significance of this study can be summed up as aiding the electricity industry's operators in administering effective energy management, efficient resource allocation, and informed decision-making.

Historical-based bidding strategy in transactive energy market for household: Data driven analysis

The energy market design is changing to enable distribution-level transactions in smart cities, encouraging end-users to participate efficiently in the market. The Transactive Energy (TE) concept opens the floor for a new market settlement philosophy that can benefit the end-user and Distributed Generators (DGs). The bidding of the customers in the distribution level market raises many concerns in the latest reports due to many factors (e.g., lack of information about the participant’s flexibility). This paper proposes a non-intrusive bidding strategy to enhance the accuracy of the household’s participation in the transactive electricity market. The proposed model utilizes the historical household user energy consumption to build the thermal model and develop the bidding strategy. The proposed approach examines the bidding in the context of user preferences of the total consumption, time at bidding, day of bidding, and ambient temperature. The results prove that the proposed strategy can significantly improve the flexibility’s recognition of the customers’ participation in the transactive market. Finally, the efficacy of the bidding method is examined via numerical analysis of actual data.

Control strategies of energy storage limiting intermittent output of solar power generation: Planning and evaluation for participation in electricity market

AbstractRenewable energy generation cannot be consistently predicted or controlled. Therefore, it is currently not widely used in the electricity market, which requires dependable production. In this study, reliability‐ and variance‐based controls of energy storage strategies are proposed to utilize renewable energy as a steady contributor to the electricity market. For reliability‐based control, photovoltaic (PV) generation is assumed to be registered in the power generation plan. PV generation yields a reliable output using energy storage units to compensate for PV prediction errors. We also propose a runtime state‐of‐charge management method for sustainable operations. With variance‐based controls, changes in rapid power generation are limited through ramp rate control. This study introduces new reliability and variance indices as indicators for evaluating these strategies. The reliability index quantifies the degree to which the actual generation realizes the plan, and the variance index quantifies the degree of power change. The two strategies are verified based on simulations and experiments. The reliability index improved by 3.1 times on average over 21 days at a real power plant.

Integrated Policies to Reduce Australia’s Electricity Sector Greenhouse Gas Emissions to Net Zero by 2050

Recent events within the Australian National Electricity Market have demonstrated that the system of an energy-only market (a market that only compensates power that has been produced) is no longer fit for purpose. The rate of change in installed capacity and generation requires better planning to ensure reliability is maintained at the lowest total system cost during the transition to net zero. Australian National Electricity Market participants will need sufficient incentives and confidence to invest in new capacity. This paper assesses a “no constraints” scenario and recommends a range of policy and market mechanisms that could be utilized to achieve a net zero National Electricity Market in Australia by 2050. This paper adopts the perspective of total system cost, which allows multiple factors relating to decision-making to be incorporated. In the absence of a carbon price, this paper seeks to put forward technology-based policy and market mechanisms to incentivise the changes required. The “Modelling Energy and Grid Services” model used in this study has shown that this “no constraints” future grid will need to contain approximately 100 GW of variable renewable energy, almost 20 GW of firm, low-emissions generation, such as carbon capture, utilisation and storage, bioenergy with carbon capture and storage, hydroelectric power, or nuclear power. It will also require more than 10 GW of storage, including pumped hydro energy storage and other energy storage technologies, and over 30 GW of firm, dispatchable peaking plants, including thermal power generation.

Informed Prosumer Aggregator Bidding Strategy via Incorporating Distribution Grid Outage Risk Predictions

FERC Order 2222 paves the way for aggregated distributed energy resources (DERs) participation in the wholesale electricity market. A particular DER assumed to be widely available in the future is the distributed prosumer (DP), also called virtual power plant (VPP), which may host PV generation, and stationary and mobile battery energy storage systems, in addition to the on-site passive load. DP aggregation and participation in the day-ahead market ancillary service products (ASPs) require managing uncertainties associated with load consumption and photovoltaic generation, electric vehicle (EV) scheduling, market-clearance prices, etc. Outages in the distribution grid may distort these energy-limited resources from their optimal operating point, potentially impacting their ability to deliver the committed ASPs in real-time. To address these challenges, first, we develop a machine learning algorithm to predict the risk of outages in distribution feeders. Next, we incorporate the distribution feeder State of Risk (SoR) predictions with the bidding model of the DP aggregator to provide an informed decision-making tool for optimal participation in the energy and ASP markets. The simulation results demonstrate the efficacy and scalability of the proposed model in improving the aggregator profitability and preventing penalties for the inability to deliver ASPs due to unexpected energy capacity limits of DP assets.

Resource-specific Orders in European Day-ahead Market Under Different Pricing Rules

This paper addresses two issues that concern the electricity market participants under the European day-ahead market (DAM) framework, namely the feasibility of the attained schedules and the non-confiscation of cleared volumes. To address the first issue, new resource-specific orders, i.e., thermal orders for thermal generating units, demand response orders for load responsive resources, and energy limited orders for storage resources, are proposed and incorporated in the existing European DAM clearing problem. To address the second issue, two approaches which lead to a non-confiscatory market are analyzed: ① discriminatory pricing with side-payments (U.S. paradigm); and ② non-discriminatory pricing excluding out-of-money orders (European paradigm). A comparison is performed between the two approaches to investigate the most appropriate pricing rule in terms of social welfare, derived revenues for the sellers, and efficiency of the attained results. The proposed model with new resource-specific products is evaluated in a European test system, achieving robust solutions. The feasibility of the attained schedules is demonstrated when using resource-specific orders compared with block orders. Finally, the results indicate the supremacy of discriminatory pricing with side-payments compared with the current European pricing rule.

A hybrid day-ahead electricity price forecasting framework based on time series

Electricity price forecasting (EPF) plays an indispensable role in the decision-making processes of electricity market participants. However, the complexity of electricity markets has made EPF increasingly difficult. Currently, popular methods for EPF are based on signal decomposition and suffer from computational redundancy and hyperparameter optimization challenges. In this paper, we propose a new hybrid forecasting framework to improve the forecasting accuracy of day-ahead electricity prices. The proposed model consists of three valuable strategies. First, an adaptive copula-based feature selection (ACBFS) algorithm based on the maximum correlation minimum redundancy criterion is proposed for selecting model input features. Second, a new method of signal decomposition technique for EPF field is proposed based on decomposition denoising strategy. Third, a Bayesian optimization and hyperband (BOHB) optimized long short-term memory (LSTM) model is used to improve the effect of hyperparameter settings on the prediction results. The effectiveness of the different techniques was broadly cross-validated using five datasets set up for the PJM electricity market, and the results indicated that the proposed hybrid algorithm is more effective and practical for day-ahead EPF.

Optimization and self-dispatching of hydro-power companies in the electricity market

The deepening reform of the power system has resulted in increased competition between electricity market participants. The ADP method is applied to solve the optimal self-dispatch problem of hydro-power companies under uncertain conditions. Firstly, according to the characteristics of hydropower generation technology and self-dispatching, the operation model of hydropower is given. Then, according to the organization and trading behavior of the forward contract market and day-ahead market, a medium and long-term contract quantity decision framework based on stochastic programming is given. Based on the stochastic programming decision framework, the ADP method is used to solve the generation and water decisions in each stage, and the distribution strategy of the electricity quantity of forward transactions and day-trading electricity quantity is obtained. Finally, an example is given to demonstrate the effectiveness of the proposed model and ADP method.