71 results about "Power planning" patented technology

The invention discloses a multi-scene coupled extreme weather adaptive power system planning method and system, belongs to the technical field of power system planning, and aims to solve the problem that traditional planning does not fully consider extreme weather influence and does not integrate multi-energy complementarity. Comprising the steps of collecting installed capacity, historical weather and power load data of a power grid unit; a conventional weather scene set is generated through clustering by adopting a kmeans algorithm, and an extreme weather scene set is generated in combination with types of extreme high temperature, cold waves and the like; constructing operation models and policy constraints of the thermal power unit, the new energy unit and the electrochemical energy storage unit; based on the planning-operation coupling framework, establishing a two-stage stochastic programming model with the goal of minimizing the total investment and operation cost; and integrating the multi-scene solving model, and outputting an adjustment power supply planning scheme. Through multi-scene coupling and two-stage optimization, planning and operation collaboration is realized, the economy, safety and adaptability of the power system in extreme weather are improved, and technical support is provided for low-carbon transformation.

The invention relates to an energy management method and system for a green electricity hydrogen production and hydrogenation all-in-one machine, and relates to the technical field of hydrogen energy application, the system comprises an upper layer control system and a communication interface module, collaborative optimization scheduling is executed in the day-ahead stage, the rolling stage and the real-time stage; the communication interface module supports IEC104, private UDP and other industrial protocols, and realizes real-time data interaction with a green electricity prediction system and a hydrogen production DCS system. The method comprises the following steps: making an electrolytic cell start-stop and power plan in a day-ahead stage; periodically correcting prediction and demand errors in a rolling stage; the power of the electrolytic cell is dynamically adjusted to fluctuate along with green electricity in the real-time stage. According to the invention, cross-section and multi-time scale coordination control is realized, and the green power consumption rate, the system operation economy and the hydrogen energy supply reliability are improved.

The invention discloses a chip design method, chip design equipment and a medium, and relates to the technical field of chips, during chip design, a target module in a chip is firstly determined, power supply planning of the target module is independently adjusted to avoid the influence of voltage drop on crosstalk when the wiring density is too large, crosstalk prevention is started in advance in the power supply planning stage, and the crosstalk is prevented from being damaged. After the layout and wiring design of the chip is carried out according to the power supply plan and the module layout, the crosstalk condition existing in the chip is directly analyzed, and if the crosstalk occurs in a target module, a mode of enlarging the layout space of the target module is adopted to cope with the crosstalk; if crosstalk occurs in other modules, a mode of adjusting electrical parameters of a signal line is adopted to cope with the crosstalk. Crosstalk prevention is carried out in the chip design stage, and different response modes are adopted according to different areas where crosstalk is located, so that the influence of crosstalk on normal working of the chip is avoided, and the accuracy and stability of the chip during working are improved.

The invention belongs to the crossing field of power system dispatching automation and artificial intelligence, and particularly relates to a parameter dynamic generation technology based on cooperation of a large model and a mechanism model. Comprising the following steps: S1, receiving natural language instruction input of a dispatcher; s2, intention recognition and instruction analysis are carried out through the power planning model, and key scheduling parameters are extracted; s3, the analysis result is converted into mathematical parameters which can be executed by the mechanism model; S4, the mechanism model carries out multi-objective optimization calculation based on the input parameters, and a preliminary scheduling scheme is generated; s5, performing semantic verification on the preliminary scheme through the large model; and S6, dynamically adjusting the parameter weight according to the verification result, and iteratively optimizing the scheduling scheme. Through deep fusion of natural language processing and a power system physical mechanism, full-process intelligent conversion and closed-loop optimization from a dispatcher instruction to a mathematical model parameter are realized, and limitation of a traditional static rule is broken through.

The invention discloses an EMIR verification method and system, a computer and a storage medium. The method comprises the following steps: appointing a time sequence library file directory, an RC file path and a constraint file path when an automatic script runs; traversing a time sequence library directory through an automatic script, analyzing time sequence library files, and extracting a PVT condition and an RC model corresponding to each file; automatically classifying and mapping the extracted PVT condition and RC model according to a preset classification rule to generate a multi-process corner combination; automatically generating a multi-mode multi-corner-point MMMC configuration file according to the multi-process corner point combination, and outputting a traceable mapping list and an association table; in a chip physical implementation process, dual-stage EMIR verification is executed in a power supply planning stage and a verification stage. According to the method, the MMMC configuration file matched with the angular point is automatically analyzed based on the time sequence library, and staged EMIR verification is combined in the physical implementation process, so that the overall design efficiency and reliability are improved.

This invention discloses a method, apparatus, equipment, medium, and product for power configuration in clean energy bases, belonging to the field of power configuration technology. The method for power configuration in clean energy bases includes the following steps: obtaining demand data for various power configurations; constructing a power configuration model for the clean energy base based on the demand data; and generating a power configuration scheme for the clean energy base using the power configuration model. This invention constructs a power configuration model applicable to integrated wind, solar, coal gas, and hydrogen storage systems. It eliminates repetitive manual work, significantly shortens the design workflow, improves power planning and design efficiency, and eliminates reliance on manual experience, enhancing the scientific rigor and standardization of various power configuration schemes, improving the quality of power planning and design, and reducing power planning and design costs, thereby promoting the development of clean energy bases.

The invention discloses a conventional unit installed capacity estimation method and system based on a load characteristic index, and belongs to the technical field of power system planning. The method comprises the following steps: acquiring historical load information, and calculating daily load and annual load characteristic indexes; deriving and planning annual total power consumption based on indexes, and calculating the minimum installed capacity of a conventional unit through annual and typical daily power balance; and energy storage peak regulation parameters are further calculated, and climbing verification and power receiving correction are carried out. The system comprises a data module, an index module, a capacity module and a correction module. The time sequence characteristics are quantified through the key load indexes, the complex power source planning process is simplified, rapid and accurate estimation of the installed capacity is achieved, the method is suitable for a new energy high-permeability system, and the planning efficiency and economical efficiency are improved.

The invention belongs to the technical field of AC / DC hybrid power grid reactive power planning, and particularly relates to a target scene-oriented AC / DC hybrid power grid reactive power planning parameter optimization method, which comprises the steps of S1, establishing a reactive power planning model considering reactive power equipment distribution, capacity and internal parameters, and introducing a reduced-order mapping matrix to pre-reduce variable dimensions; s2, performing simplified linearization processing on the transient stability constraint optimal power flow problem of the power system, and performing analysis and processing to obtain the linearization stability constraint of the reactive power planning model; s3, removing the corresponding minimum probability distance scene from the set until the representative scene is equal to a preset value; s4, integrating the linearization stability constraint of the reactive power planning model and the representative scene set into the reactive power planning model to obtain an optimal power system reactive power planning model; and S5, performing dynamic reactive power planning by using the optimal power system reactive power planning model. According to the method, the planning efficiency can be effectively improved on the premise of ensuring the voltage qualification rate.

The invention discloses a power distribution network reactive power planning method based on an improved point estimation method and chance constraint, and the method comprises the steps: S1, carrying out the mixing moment calculation and sample point selection of an uncertainty parameter through employing the improved point estimation method, and obtaining an estimation value of the uncertainty parameter; the uncertainty parameters comprise distributed power supply output and load; s2, constructing a power distribution network reactive power planning model based on opportunity constraint, taking the minimum comprehensive operation cost of the power distribution network as a target function, and determining various constraint conditions; the constraint conditions comprise a power flow equation equality constraint of the power distribution network, an inequality constraint of a node voltage amplitude, branch current and reactive compensation equipment capacity, and a chance constraint of the node voltage amplitude and branch power; and S3, substituting the estimated values of the uncertainty parameters into the reactive power planning model, and solving the reactive power planning model by adopting a genetic algorithm combined with quantum behaviors. According to the method, the defects of a traditional point estimation method and deterministic constraints are overcome, and a better reactive power planning scheme is obtained.

The invention provides an electric power planning method for renewable green new energy development, and belongs to the technical field of energy planning, and the method comprises the steps: calibrating a plurality of supply points in a region according to the position of each electric device in the current region and the type of an energy demand in combination with a change plan; performing preliminary modeling on each building in the area, and inferring an energy transformation scheme by combining the energy demand quantity and the energy demand type designed by each supply point; transmitting energy generated by the new energy system to a plurality of corresponding electric devices for consumption; and the new energy system is integrated into the current actual construction scheme and the building construction scheme to be carried out in the future, and finally energy supply transformation of the buildings in the area is completed. According to the electric power planning method for renewable green new energy development, the proportion of new energy supply of the whole area can be increased, efficient nearby consumption of energy is achieved, dependence on traditional energy is reduced, and a limited new energy system structure is optimized.

The application provides a multi-time scale power supply guarantee analysis method and system, which comprises the following steps: collecting load parameters in a system to be studied; performing load characteristic analysis and new energy characteristic analysis based on the load parameters to obtain preliminary typical day simulation analysis results; performing typical day simulation calculation based on the preliminary typical day simulation analysis results to obtain an intraday power supply guarantee result, and ending the power supply guarantee analysis if the system has no power shortage; if there is a power shortage, performing the next step of analysis; if there is a power shortage, performing monthly power balance calculation to measure seasonal power shortage, and formulating a seasonal power supply guarantee scheme; after the seasonal power supply guarantee scheme is adopted to ensure seasonal power balance, performing continuous multi-day power balance calculation to measure continuous multi-day peak shaving demand, formulating a continuous multi-day power supply guarantee scheme according to the size of the extreme weather power shortage, and performing typical day simulation analysis again if there is no power shortage. The method can quantitatively analyze the peak demand of different time scales in the system during the power supply guarantee period, and provide support for power source planning.

This invention belongs to the field of power planning and new energy power generation. It discloses a method, system, equipment, and medium for configuring the capacity of an amphibious power plant based on monthly balance. Based on the load forecast of the amphibious power plant and the predicted new energy power generation during the hydropower peak and off-peak seasons, a monthly power balance analysis of the amphibious power plant is performed to obtain the power deficit for each power-deficient month and the power balance for each power-excessive month. Based on the power deficit for each power-deficient month, the required coal-fired power generation capacity to ensure power supply during each power-deficient month is determined, and the maximum value is selected to obtain the coal-fired power generation capacity of the amphibious power plant. Based on the power balance for each power-excessive month, the required energy storage capacity to ensure the complete consumption of abandoned new energy power during each power-excessive month is determined, and the maximum value is selected to obtain the energy storage capacity of the amphibious power plant. This achieves a reasonable determination of the coal-fired power generation capacity and the energy storage capacity of the amphibious power plant.

This invention belongs to the field of power planning and design technology, and discloses a method and system for simulating wind farm output. The method first calculates the theoretical output, stochastic reduction factor, low temperature reduction factor, and maintenance reduction factor based on the target basic data of the project location, and calculates the hourly comprehensive reduction factor. Then, the actual output is calculated based on the theoretical output and the hourly comprehensive reduction factor. In this way, the impact of uncertainties such as temperature and maintenance on the output during the actual operation of the wind farm is taken into account. Based on mesoscale reanalysis data or measured wind speed data, it can quickly and accurately simulate the actual output data of the wind farm without the need for a complex modeling process, which can meet the needs of wind power project output prediction.

The present application relates to the technical field of data processing, and especially relates to a power planning optimization method based on artificial intelligence, which comprises the following steps: collecting data; determining abnormal events; predicting parameters; determining candidate shutdown equipment; determining high-risk equipment; determining target shutdown equipment; generating a power planning scheme; and adjusting thresholds. The present application collects multi-dimensional data in real time, determines abnormal events according to total power consumption, predicts load loss and residual time in combination with a preset model, determines high-risk equipment according to residual time, heat consumption rate, vibration frequency and rotor speed, determines target shutdown equipment according to active power, climbing rate and load loss of high-risk equipment, and adjusts thresholds dynamically according to total power consumption and rotor speed based on the power planning scheme, thereby effectively solving the problems of low precision of shutdown decision and response lag caused by the complexity of the operation background of the power system and excessive dependence on models.

The application discloses a novel power system multi-dimensional supporting demand index evaluation method and system, belongs to the field of power system demand estimation, and comprises the following steps: based on system load data and new energy output data, analyzing power system net load data conditions; based on the power system net load data conditions, screening extreme weather new energy continuous low output data according to the new energy output data, determining an extreme weather time segment, and acquiring extreme weather period net load data; and based on the extreme weather period net load data and total time sequence net load data, determining a supporting demand index in the time sequence, and supporting new power system power sources for planning. The application more comprehensively constructs a multi-dimensional supporting index system of supporting power sources, and provides a reference basis for new power system supporting power source planning.

The invention relates to the field of power distribution network reactive power optimization, and discloses a reactive power planning optimization method and system for a high-voltage power distribution network, and the method comprises the steps: obtaining real-time power data collected by a sensor, calculating a reactive power demand, and obtaining reactive power demand distribution; when the variance of the reactive power demand distribution exceeds a preset threshold value, the compensation capacity is adjusted, and a preliminary planning scheme is obtained; simulating an operation state according to the preliminary planning scheme, and obtaining a voltage deviation; when the voltage deviation value is larger than a preset threshold value, parameters are dynamically adjusted, and refining scheme output is obtained; reactive power compensation capacity is adjusted according to the refining scheme output, a first reactive power compensation scheme is obtained, reactive power distribution is optimized according to the first reactive power compensation scheme, a final reactive power optimization scheme is obtained, reactive power compensation parameters are adjusted according to the final reactive power optimization scheme, and final reactive power optimization configuration is obtained. According to the method, a reactive power planning scheme adapting to dynamic characteristics and prediction deviation can be constructed in the face of load random change.

The invention relates to a reverse deduction power system planning method, which comprises the following steps of: obtaining a long-term annual total installed capacity target in a long-term planning layer; in the middle-term coordination layer, an adjusted long-term annual total installed capacity target is obtained; in the short-term verification layer, outputting a final long-term annual total installed capacity target; the long-term planning layer, the middle-term coordination layer and the short-term verification layer jointly form a long-term-middle-term-short-term three-layer coupling deduction framework, and iterative optimization circulation of verification is operated from bottom to top. According to the method, a long-term-middle-term-short-term three-layer coupling deduction framework is constructed, reverse solution is carried out with the carbon peak reaching target year as rigid constraint, the problem that long-term strategy and short-term operation are disjointed frequently occurring in traditional electric power planning is effectively solved, the planning result has perspectiveness, and the method is suitable for large-scale popularization and application. The scientificity and the performability of the planning scheme are obviously improved; the total economic cost of low-carbon transformation of the whole power industry is effectively reduced, and collaborative improvement of economy and reliability is achieved.

The application discloses an abnormal power meteorological data correction method and device for power planning, relates to the power technology field, and mainly aims to improve the accuracy of power system operation and planning. The main technical scheme of the application is as follows: obtaining initial power meteorological data sequences corresponding to each meteorological parameter in each transformer substation; constructing a power grid topology graph according to the initial power meteorological data sequences, the topology structure of a power transmission network, the geographical relationship between each transformer substation and the admittance matrix relationship; determining the space-time correlation characteristics between each node in the power grid topology graph based on a preset construction method; identifying abnormal data in the initial power meteorological data sequences corresponding to each meteorological parameter in each transformer substation based on the power grid topology graph and the space-time correlation characteristics between each node; and correcting the abnormal data according to the space-time correlation characteristics between each node and a preset data correction rule to obtain optimized power meteorological data, so that power planning is performed according to the optimized power meteorological data.

The application discloses a kind of combination clustering scene reduction method and system based on potential decision result, the uncertainty factor of each node in power system is expressed as multidimensional curve input domain in the form of time sequence curve;Based on multidimensional curve input domain, the power supply planning problem solving model under different time scale scene is constructed, considering operation checking, multidimensional curve input domain is converted into potential decision result domain for clustering analysis;SOM neural network clustering is carried out to potential decision result, and preliminary clustering result is obtained;SOM and k-medoids combination clustering method is used to finally classify preliminary clustering result, and finally the typical scene used in operation checking is obtained.The application is used to cluster the most representative scene set in power supply planning typical scene operation checking, to reduce the complexity of solving model to the greatest extent under the condition of guaranteeing the reliability of checking result, improve calculation efficiency.

The invention relates to an electric power planning report three-level title structured analysis generation method and device and a medium, and the method calls a large language model to execute the following steps: obtaining a to-be-processed electric power planning report and carrying out report paragraph text extraction to obtain an original text; segmenting the original text into overlapped text blocks, wherein the overlapped part comprises a three-level title context; constructing a power planning professional cue word, for each text block, identifying a three-level title in a specific format, classifying sub-section contents into a corresponding three-level title text, and outputting an analysis result; and detecting repeated contents in analysis results of adjacent text blocks, eliminating repetition based on text tail fix matching, integrating the analysis results of all the text blocks, generating a structured result containing three-level titles, corresponding texts, analysis time and text statistical information, and performing structural optimization. Compared with the prior art, the method has the advantages of high three-level title recognition accuracy, high structured data format compliance rate and the like.

The invention discloses an offshore wind power AC / DC power transmission planning method and device, electronic equipment and a storage medium, and belongs to the technical field of power planning, and the method comprises the steps: constructing a multi-stage probability planning model corresponding to a power system according to the multi-source data of the power system, and then according to the multi-stage probability planning model, constructing a multi-stage probability planning model corresponding to the power system; constructing a corresponding objective function and a constraint condition by taking the minimum total air transportation cost of the power system as an objective; under the constraint of the constraint condition, solving the target function to obtain the total wind transportation cost, the number of newly added lines, the wind power installed capacity and the power transmission power of a generator set corresponding to the power system when the total wind transportation cost of the power system is minimum; according to the method, the planning scheme of the offshore wind power AC / DC power transmission is obtained, and then the offshore wind power AC / DC power transmission planning is carried out according to the planning scheme, so that the problem that no related technical means exists in the prior art to realize scientific offshore wind power transmission planning can be solved.

The application discloses a kind of intelligent network connection plug-in hybrid electric bus electric quantity planning methods, comprising: the speed curve of the intelligent network connection plug-in hybrid electric bus of fixed route operation is collected as typical working condition, the optimal variation curve of battery state of charge (SOC) of typical working condition is obtained using global planning algorithm, the interval power consumption of each working condition segment is extracted and the interval power consumption identification model based on the characteristics of working condition segment is constructed, on the basis, the best electric quantity planning value of next working condition segment is determined by introducing improved interactive multi-model algorithm, and the limitation of single electric quantity distribution mode is eliminated.The application realizes the optimal planning of the electric quantity of intelligent network connection plug-in hybrid electric bus, and focuses on solving the problem of vehicle energy consumption deterioration caused by unreasonable electric quantity distribution, which has great theoretical and practical value for deeply tapping the energy-saving and emission-reducing potential of plug-in hybrid power system and promoting the green and sustainable development of urban public transportation.

The invention discloses a power expansion planning method based on flexible resources and a related device. The method comprises the following steps: acquiring historical data of a target area, and power planning data and prediction data in a planning year; optimizing the target flexibility model through the preprocessed historical data and prediction data; carrying out flexibility planning solution according to power planning data through the optimized target flexibility model, and outputting planning information by taking the minimum sum of investment cost, operation and maintenance cost, unsatisfied load, excessive power generation and renewable energy source abandoning cost and flexibility default cost as a target function under the condition of satisfying model planning constraints; and performing extension path analysis according to the planning information, and generating a power extension planning strategy considering both economy and flexibility.

The invention relates to an alkaline electrolytic cell and PEM electrolytic cell power plan making method and device and a computer storage medium, and belongs to the technical field of hydrogen production. Predicted power of new energy power generation and actual power of the electrolytic cell are obtained, when the predicted power is larger than the actual power, power plans of the alkaline electrolytic cell and the PEM electrolytic cell are made according to the deviation value between the predicted power and the actual power, and the sum of the power of the alkaline electrolytic cell and the power of the PEM electrolytic cell can absorb the deviation value; and when the predicted power is not greater than the actual power, formulating power plans of the alkaline electrolytic cell and the PEM electrolytic cell according to a deviation value between the actual power and the predicted power, so that the sum of the power of the alkaline electrolytic cell and the PEM electrolytic cell can compensate the deviation value. According to the method, the power plan of the alkaline electrolytic cell and the PEM electrolytic cell is formulated by utilizing the deviation value between the predicted power of new energy power generation and the actual power of the electrolytic cell, so that the timeliness and the accuracy of control are improved, and the electrolytic cell keeps relatively high hydrogen production efficiency in hydrogen production.

The invention discloses a low-voltage transformer area loss reduction optimization method suitable for photovoltaic grid connection, belongs to the technical field of power system optimization and new energy grid connection, and aims at challenges such as voltage fluctuation and network loss increase caused by distributed photovoltaic grid connection to construct a load flow calculation model through multi-source data through processing. The investment construction cost, the operation maintenance cost and the network loss cost are comprehensively considered, an optimization model with loss reduction as a target is established, the model fuses conventional power flow constraints, power quality constraints and to-be-planned equipment operation constraints, and efficient solving is performed by adopting a mixed solving algorithm of generalized Benders decomposition and an external approximation algorithm; and finally, outputting energy storage, reactive power planning and other loss reduction optimization schemes and an optimized line loss result. The economical efficiency and safety of the low-voltage transformer area are effectively improved, and scientific support is provided for power distribution network line loss management.

The invention discloses a power distribution network low-carbon planning method, system and device considering carbon emission flow and a storage medium, and relates to the technical field of electric power planning, and the method comprises the steps: collecting the planning basic data of an electric power system, taking the minimum investment cost and operation cost as the target, building a target function, coordinating and optimizing the investment building capacity of a traditional unit, renewable energy sources and stored energy, and building an upper-layer investment planning model; constructing a lower-layer demand response model based on the unit output and line power flow data calculated by the upper-layer investment planning model; based on the upper-layer investment planning model and the lower-layer demand response model, constructing a power system double-layer low-carbon planning model; performing iterative solution on the double-layer low-carbon planning model of the power system to obtain a power distribution network planning result; the method can reduce the carbon emission and demand response cost of the load side and the energy storage system, guarantees the stability of a power grid through load adjustment and carbon emission constraint, improves the energy utilization efficiency, and promotes all subjects in the power market to participate in demand response.

This disclosure relates to the field of power system technology, and discloses a method, apparatus, equipment, and storage medium for medium- and long-term power planning based on the characteristics of next-generation coal-fired power plants. The method involves constructing a first multi-dimensional operational constraint for next-generation coal-fired power units based on multi-dimensional characteristics, including clean energy reduction, safety, efficient regulation, and intelligent operation. A second multi-dimensional operational constraint is constructed based on the requirements for multi-source coordinated operation. A target constraint system for next-generation coal-fired power units is then constructed based on the first, second, and comprehensive cost constraints. The initial installed capacity scheme is iteratively optimized using a target time-series production model combined with the target constraint system to obtain the target installed capacity scheme. Through the first multi-dimensional operational constraint, the four core characteristics of clean energy reduction, safety, efficient regulation, and intelligent operation are accurately covered, effectively solving the problem of inaccurate characterization of coal-fired power plants.

The application discloses a power source structure evolution simulation method, device and system for a capacity-energy market, comprising the following steps: taking a target year as a cycle termination condition, cyclically executing a power source structure evolution evaluation and analysis step, and obtaining a power system power source structure evolution evaluation and analysis result; specifically, obtaining energy market clearing quantity and clearing price based on market data of a current year; obtaining initial capacity investment decisions of power generation enterprises based on the energy market clearing quantity and the clearing price; obtaining capacity market clearing quantity and clearing price based on the initial capacity investment decisions of the power generation enterprises; obtaining final capacity investment decisions of the power generation enterprises based on the capacity market clearing quantity and the clearing price; and obtaining a power source structure evolution condition of the current year and market data of the next year according to the final capacity investment decisions of the power generation enterprises. The application can effectively improve the accuracy of power source structure evolution analysis under a power market environment, and can assist long-term power source planning and capacity market mechanism design.

The application relates to the technical field of power planning, and provides an AI-based virtual power plant energy supply and demand accurate matching method and system, which solves the problems of low accuracy and overall operation efficiency of virtual power plant energy supply and demand matching. The method comprises the following steps: collecting output data sequences of power supply equipment in a virtual power plant and electricity price data sequences of a power market; dynamically adjusting initial charging and discharging power of energy storage equipment in the virtual power plant to obtain target charging and discharging power; using a federal learning mode to fuse and optimize load prediction models of each energy participating node in the virtual power plant to generate a global demand regulation plan; generating a power dispatching plan based on the output data sequences and the electricity price data sequences; and applying the power dispatching plan and the global demand regulation plan to energy supply and demand matching of the virtual power plant in a cooperative manner to realize AI-based virtual power plant energy supply and demand accurate matching. The application improves the accuracy and overall operation efficiency of virtual power plant energy supply and demand matching.

The application discloses a kind of based on deep Q network's directional energy deposition laser power offline planning method, belong to the field of additive manufacturing.The numerical model of macroscopic temperature field based on directional energy deposition process is constructed as interactive environment, the volume of molten pool is extracted as the state feature of heat process, and the target molten pool volume is determined by experiment calibration.The power planning problem is constructed as Markov decision process, the state vector consisting of molten pool volume sequence, discrete power adjustment action set and Gaussian reward function centered on target volume are defined, and the deep reinforcement learning framework is formed.Under this framework, the deep Q network agent is trained to learn the optimal power adjustment strategy.Finally, the laser power sequence of the deposition process is planned offline using the trained agent.The application can plan the optimal laser power sequence offline, stabilize the heat input of directional energy deposition process, effectively suppress defects such as incomplete fusion and cracks, and improve the quality of additive manufacturing.