22 results about "Economic optimum" patented technology

The invention discloses a gas storage integrated operation model construction method and system based on digital and intelligent twinning, and relates to the field of gas storage integrated operation model construction, and the method comprises the steps: constructing a single well IPR and VLP curve; a mode of combining forward pressure regulation and reverse pressure regulation is adopted, a pressure value set of all nodes after pressure stabilization is output, and a preliminary pressure steady-state scheme is formed; an economic value evaluation index function is constructed, and the total daily operation cost of the system under the given gas production rate is evaluated; a comprehensive optimization model based on a neural network is constructed, and injection-production quantity reference values of all wells and target values of all nodes are output; and verifying the stability of the comprehensive optimization model based on the neural network according to the output injection-production quantity reference values of all wells and the target values of all the nodes. The method has the advantages that the physical law of gas storage injection and production, the system pressure balance and the economical efficiency target are deeply fused, and a fast and reliable closed loop from pressure steady-state optimization to an economical optimal decision is achieved.

The invention relates to the field of sewage treatment, and discloses an energy-saving optimization control method and system for a sewage treatment aeration system based on multi-source information fusion, and the method comprises the steps: firstly, collecting the quality and quantity of inlet water, the environment of a biological tank and an external electricity price signal in real time; then, dynamically calculating a dissolved oxygen set value through a threshold weight rule model based on water inlet parameters, generating a preliminary control instruction by taking the dissolved oxygen set value as a feedforward target, and meanwhile, performing feedback fine tuning in combination with an actual dissolved oxygen value in the pool; a multi-target reward function fusing water quality, energy consumption and stability targets is constructed, the weight of the multi-target reward function is dynamically adjusted according to the real-time electricity price, and an economically optimal dissolved oxygen set value correction instruction is decided through optimization; according to the method, advanced accurate control of aeration requirements and online optimization of operation cost are realized, the problems of response lagging and high energy consumption of traditional control are effectively solved, the stability of effluent quality is remarkably improved, and energy consumption is reduced.

The invention provides an optimal scheduling method for a carbon capture power plant under a carbon background, and belongs to the technical field of carbon capture, and the method specifically comprises the steps: constructing a carbon emission prediction model and the carbon capture cost of the carbon capture power plant; based on the carbon emission permit transaction price, the power coal price, the fuel oil price, the certification index and the carbon quota quantity, a prediction model based on a machine learning algorithm is adopted to obtain a carbon emission permit prediction transaction price; according to the method, based on the carbon quota of a carbon capture power plant and the accumulated carbon emission of the carbon capture power plant, optimal scheduling stages of the carbon capture power plant are divided, and based on different optimal scheduling stages of the carbon capture power plant, carbon capture cost, a carbon emission permit prediction transaction price, a load output requirement and a carbon emission prediction model, economic optimization is taken as a target. The optimization scheduling of the carbon capture equipment, the energy storage equipment and the load output of the carbon capture power plant of the carbon capture power plant is realized, so that the reliability and the accuracy of the optimization scheduling model of the carbon capture power plant are ensured.

The invention discloses a farmland soil nitrogen rapid estimation and variable fertilization decision-making method based on remote sensing-ground coordination, and belongs to the technical field of intelligent agricultural variable fertilization. According to the method, farmland planar canopy spectral information is rapidly obtained through multi-spectral remote sensing of an unmanned aerial vehicle, ground sampling points are synchronously arranged, soil alkali-hydrolyzable nitrogen is actually measured and serves as a true value, two types of data are fused through incremental learning and spatial Bayesian assimilation technologies, an inversion model is updated online, and a high-precision nitrogen spatial distribution diagram is generated; further constructing a'nitrogen-crop-economy 'integrated dynamic optimization model, taking unit area economic net income maximization as a target, combining a crop nitrogen response function, a fertilizer cost and an agricultural product price, calculating an economic optimal fertilization amount of each grid, introducing fertilization risk entropy to quantify uncertainty, and dynamically adjusting a prescription map; finally, minute-level variable fertilization execution is achieved through an edge computing node embedded into an agricultural machine terminal, operation data is transmitted back to a cloud end for model retraining, and a closed loop is formed.

The invention relates to the technical field of AGC coordinated control, and discloses an AGC coordinated optimization control system based on multi-source data fusion, and the system carries out the collection and normalization preprocessing of multi-source data through a multi-source data collection module, and forms a global multi-dimensional data set; constructing a risk model through a data driving module, outputting a minimum reserve capacity demand adaptive to a current system risk level, and determining safety demands and economic boundaries under different working conditions through working condition discrimination and economic cost benchmark calculation; a hierarchical multi-objective optimization model is constructed through an intelligent optimization module, and a resource allocation scheme considering a safety base line and economic optimization is solved; and disassembling the optimal decision scheme into personalized instructions adaptive to various resource physical characteristics through a personalized adjustment module. And finally, an AGC coordination optimization mechanism with dynamic balance of safety and economy is constructed, and the problem of contradiction between standby capacity guarantee safety and control cost is solved accurately.

The invention discloses an electrolytic bath self-adaptive energy management and control method and system applied to wide power fluctuation, and relates to the technical field of energy management and control, and the method comprises the following steps: S1, based on external prediction information and internal demands, generating a predefined power instruction curve through rolling optimization of a model prediction control algorithm, the optimal economical efficiency or the highest energy utilization rate is achieved, and the comprehensive operation performance of the electrolytic cell under the wide power fluctuation condition is remarkably improved by constructing a three-layer intelligent control framework of'predictive scheduling-self-adaptive coordination-rapid execution '. The upper layer adopts a model predictive control algorithm, combines external weather, electricity price and internal hydrogen production demand, generates a power instruction curve with optimal economic and energy efficiency in a rolling manner, and realizes prospective energy scheduling; a multivariable self-adaptive coordination mechanism is introduced into the middle layer, and the multivariable self-adaptive coordination mechanism comprises power-flow dynamic matching, temperature-pressure feedforward-feedback stabilization control and hydrogen-oxygen differential pressure sliding mode robust control.

This disclosure provides a method and system for controlling SO2 emissions from a circulating fluidized bed unit. By constructing a dynamic SO2 emission prediction model that includes economic objectives and adopting a hierarchical collaborative optimization control architecture, the method first uses an optimization algorithm to calculate the economically optimal SO2 concentration setpoint in real time. Then, it uses a dual-loop generalized predictive controller (GPC) for precise tracking control. At the same time, a fuzzy inference system is introduced to dynamically and adaptively adjust the weight of the control objective. This achieves stable, economical, and environmentally friendly synergistic optimization control of SO2 emissions under complex operating conditions such as deep peak shaving. It effectively solves the problems of slow response, unstable control, and high cost of traditional methods, and achieves the beneficial effects of significantly reducing desulfurization operating costs, enhancing emission concentration stability, and improving the system's adaptive capability.

The application belongs to the field of power grid dispatching, and specifically discloses a new energy power generation dispatching method facing zero examination quantity constraint. The core of realizing zero examination of the application lies in constructing an economic optimization model allowing active wind curtailment and energy storage cooperation. Traditional methods usually only rely on energy storage to smooth fluctuations, and may fail due to insufficient capacity under extreme fluctuations. The scheme internalizes the examination cost as a cost, and simultaneously takes the wind curtailment instruction and energy storage control as optimization variables, so that the model can autonomously weigh between economy and compliance. The introduced zero examination quantity constraint sets an insurmountable boundary for active power change, and the wind curtailment variable in the model ensures that when the fluctuation may exceed the limit, the system can cooperate with energy storage through the most economical wind curtailment decision to ensure that the grid-connected power strictly meets the standard. Compared with the prior art, through the wind curtailment and energy storage cooperation mechanism, a complete and feasible path for realizing zero examination is provided, and the grid-connected certainty and safety are fundamentally improved.

The present application relates to the technical field of industrial energy system optimal scheduling and intelligent control, and proposes a micro-grid multi-scenario collaborative optimization scheduling method for mine scene, which comprises the following steps: data preprocessing and system basic modeling for mine characteristics, construction of fine benchmark economic optimal scheduling model, emergency standby scheduling model based on distribution robust opportunity constraint, and collaborative optimization model of virtual power plant participating in day-ahead spot market, adoption of multi-mode adaptive switching mechanism based on rolling time domain and state discrimination to optimize model parameters, and finally integration of each module by using micro-service architecture and deployment in mine scheduling center to realize uninterrupted automatic optimization scheduling.The present application realizes the global collaboration of "economic in normal state, safety in emergency, and market in opportunity" in mine micro-grid for the first time by constructing three independent and complete optimization models of economy, emergency and market, and designing intelligent switching mechanism in the upper layer.

This invention discloses a method and system for power planning and allocation in receiving provinces that considers uncertainties. The method includes: formulating a basic power supply plan; constructing a probabilistic scenario set of annual hydropower utilization hours based on historical water inflow data; setting green and low-carbon targets and calculating the inter-provincial renewable electricity volume required to meet the renewable energy consumption responsibility weight under different scenarios; establishing an inter-provincial transaction cost model to calculate the cost per kilowatt-hour and total transaction cost for each scenario; constructing a system annual operating cost model to obtain the total system cost under each scenario and then averaging it to obtain the expected total cost; and iteratively optimizing the installed capacity of new energy sources with a fixed increment until convergence, outputting the economically optimal solution. This invention achieves a coordinated balance between the economy, greenness, and security of power allocation by probabilistically handling hydropower uncertainties and introducing inter-provincial green electricity trading as an optimization variable.

The invention relates to the technical field of energy optimization scheduling, in particular to a micro-grid reactive power optimization distribution method based on deep reinforcement learning control. The method comprises the following steps: establishing a communication link between adjacent distributed power supplies, and selecting a main containment distributed power supply; constructing a micro-grid economic optimization model, and formulating an objective function and constraint conditions of the optimization model by taking economic optimization as an objective; by adopting traction control, the marginal cost of the distributed power supplies is consistent, and the optimal control of the economic cost of each distributed power supply in the micro-grid is realized; taking the maximum deviation value of the marginal cost coefficient as an observed quantity, and obtaining a target marginal cost coefficient based on deep reinforcement learning control; and calculating a reactive power correction output target value of each distributed power supply, controlling the reactive power output value of each distributed power supply to be consistent with the correction output target value, and correcting each distributed voltage. The reactive power distribution precision is improved.

The invention provides a double-layer clearing method for the participation of a Sagomei large base in a trans-provincial and trans-regional power market. The method comprises the following steps: constructing a double-layer optimization model, operating an upper-layer model, carrying out multi-channel centralized optimization clearing, determining a total delivery electric quantity instruction of the Sagomei large base, and inputting the total delivery electric quantity instruction as a boundary condition into a lower-layer model; operating the lower-layer model, solving the optimality condition based on the optimal scheduling scheme of the lower-layer model, and obtaining the shadow price of the power balance constraint related to the total delivery power; the shadow price is used as a new declaration electricity price of the Sagomei large base to be fed back to the upper layer model; the model operation solving step is repeated, and iterative calculation is carried out until the variable quantity of the outgoing power instruction and the variable quantity of the shadow price are both smaller than a preset convergence threshold value; and outputting a final inter-province market clearing result and a large-base internal economic optimal scheduling scheme. According to the method, the transaction efficiency, the resource configuration efficiency and the power grid stability are improved.

The present application belongs to the technical field of oil and natural gas development, and particularly relates to a shale oil reservoir yield increasing and cost reducing fracturing optimization design method. The present application obtains the fracture spacing, single-stage ground liquid volume and well soaking time range by adopting high-density fine cutting and fracture forming, pre-pressing water supplementing formation energy and oil displacement agent accelerating imbibition replacement; obtains the perforation cluster number, single cluster hole number, single hole flow, plugging agent addition and temporary plugging series parameters by adopting soluble ball seat hard packer, limited flow perforation dense fracture and temporary plugging diversion soft sub-cluster; determines the economic optimal range of key engineering modification parameters by combining field big data statistical regression, single well EUR comprehensive measurement and economic index sensitivity analysis; selects the horizontal section sweet spot by establishing horizontal section reservoir segmentation and grading evaluation standard; and solves the shale oil reservoir scale benefit development problem through the steps of target block targeted shale oil reservoir yield increasing and cost reducing fracturing optimization design.

The invention relates to a new energy power system stable economic dispatching method cooperating with electric vehicle demand response and space-time flexible load, comprising the following steps: obtaining output prediction data of new energy, establishing a dispatching model of a supply side generator set and a new energy system, and embedding small signal stability constraints; an electric vehicle demand response model based on the self-adaptive time-of-use electricity price is established on a demand side, so that a charging load is converted into a schedulable resource; meanwhile, a unified space-time flexible load model is established to cooperatively schedule time and space flexible loads; and finally, in the stable economic dispatching process, implementing a two-stage optimization strategy, namely screening a dispatching scheme set meeting the small signal stability constraint in the first stage as a safety feasible region, and in the second stage, iteratively searching a dispatching scheme with an optimal system comprehensive operation index in the safety feasible region by taking the minimum total operation cost as an objective function. According to the invention, economic optimal scheduling under dynamic stability of the power grid is guaranteed.

The invention provides an energy pile reliability analysis and design method considering soil parameter spatial variability. The method comprises the steps that S1, an energy pile certainty analysis model under the thermal-hydraulic-mechanical coupling effect is selected; s2, determining a failure mode of the energy pile; s3, soil uncertainty parameters and design variables are selected, and the design space of the pile length and the pile diameter is determined based on the design variables; s4, sampling is carried out to form alternative design schemes; s5, representing the spatial variability of the thermal physical mechanical parameters of the soil body, generating a random field sample, and calculating a failure probability; s6, establishing an energy pile total probability design method based on a response surface method; s7, determining a design feasible region in the design space; and S8, selecting an optimal design scheme from the design feasible region according to an economic optimal principle. According to the method, efficient reliability analysis and design of the energy pile are achieved by fusing the heat-water-force coupling model, the efficient probability analysis algorithm and the multi-failure-mode collaborative optimization strategy.

The embodiment of the invention provides a new energy station generation power prediction method and device oriented to electricity market transactions, and relates to the technical field of new energy, and the method comprises the steps: constructing a training set through the actual electricity price data, weather forecast data, and the operation data and actual power data of a wind and light power station, constructing a test set by using the predicted electricity price data, the weather forecast data, the operation data of the wind-solar power station and the actual power data; training a wind-solar combined power prediction model by using the training set to obtain an initial wind-solar combined power prediction model; inputting the test set into the initial wind-solar combined power prediction model to obtain predicted power data; the total power generation income is calculated by combining the predicted electricity price data, the predicted power data and the corresponding actual power data; and by taking maximization of the total power generation income as a target, adjusting model parameters of the initial wind-solar combined power prediction model to obtain a target wind-solar combined power prediction model. According to the invention, power prediction can be carried out to realize economic optimization.

The invention discloses a decision-making method for efficiently returning agricultural wastes to fields to improve soil quality based on big data and artificial intelligence, and belongs to the technical field of crossing of agricultural environment engineering and intelligent agriculture. The method mainly comprises the following steps: S1, constructing an agricultural waste-treatment process-carbon-based material characteristic database and an intelligent prediction model; the method comprises the following steps: S1, constructing a carbon-based material (type / input amount)-soil health index association database and an intelligent prediction model, S3, constructing a spatial distribution data system of agricultural waste resources and soil mass distribution in a region, and S4, constructing a data-driven target region agricultural waste efficient returning-to-field driving soil fertility improvement decision optimization model. The invention aims to realize quick improvement of the soil quality of the regional cultivated land, the lowest environmental cost in the waste recycling process and the optimal economy through coupling.

The invention relates to a rice nitrogen fertilizer application amount prediction method, which comprises the following steps: firstly, constructing each rice test data sample based on multi-point nitrogen fertilizer gradient test data, then constructing a secondary mixing effect yield response model containing a fixed effect coefficient and a random effect item, and fitting to obtain a yield-nitrogen application amount response model; then, based on a yield-nitrogen application amount response model and an economic objective function, solving the highest yield nitrogen application amount and the economic optimal nitrogen application amount of each test point, then, carrying out Monte Carlo resampling and training to obtain a highest yield nitrogen application model group and an economic optimal nitrogen application model group, and finally, aiming at each position of a target to-be-tested area, carrying out optimal nitrogen application on each position of the target to-be-tested area. According to the method, the nitrogen application amount related to the highest yield target and the nitrogen application amount related to the economic optimal target are determined, then the high-resolution regional optimal nitrogen application map is formed, the design scheme has both the interpretability of an empirical model and the generalization ability of machine learning, and the decision precision of farmland nitrogen fertilizer management recommendation can be remarkably improved.

The invention discloses an optimal scheduling method, system and device for an electricity-hydrogen-ammonia-alcohol comprehensive energy system and a medium, and the method comprises the steps: obtaining all device parameters of the electricity-hydrogen-ammonia-alcohol comprehensive energy system, and building an electricity-hydrogen-ammonia-alcohol comprehensive energy system optimal scheduling model with economic optimality as a target; reconstructing the established optimal scheduling model of the electro-hydrogen ammonia-alcohol comprehensive energy system into a constrained Markov decision process, and optimizing the constrained Markov decision process by using a Lagrange multiplier; and adopting a diffusion actor-commentator algorithm considering information entropy, and combining with a Gaussian mixture model to train and solve an electric hydrogen ammonia alcohol comprehensive energy system optimization scheduling model corresponding to the constrained Markov decision process to obtain an optimal scheduling scheme. According to the method, the electro-hydrogen ammonia-alcohol comprehensive energy system can realize economic optimal scheduling on the premise of meeting multi-equipment safety constraints of thermal power generating units, wind and light, hydrogen production and hydrogen storage and the like, the scheduling solving efficiency is improved, new energy consumption is promoted, and stable and efficient operation of the system is guaranteed.

The invention provides an energy storage power station configuration and scheduling method and device, and relates to the technical field of electrical engineering and thermal engineering. The method comprises the steps of drawing up a fused salt heat storage scheme set and an electric heating scheme set of an energy storage power station based on the peak-valley electricity price duration of the day, the transformer capacity of a plant station where a reusable coal power unit is located and the turbine power of the coal power unit, and combining the fused salt heat storage scheme set and the electric heating scheme set to form an initial scheme set of the energy storage power station; constructing a multi-market collaborative optimization model by taking the maximum single-day operation net income of the energy storage power station as a target on the basis of annual time sequence electricity price and auxiliary service price data, and determining an economic optimal scheme in the initial scheme set and a corresponding economic optimal heat storage charging and discharging strategy on the basis of the multi-market collaborative optimization model; and configuring an energy storage power station based on the economic optimal scheme, and realizing scheduling of the energy storage power station based on the economic optimal heat storage charging and discharging strategy. By means of the method, economic maximization of equipment configuration and operation regulation and control of the energy storage power station is achieved.

The invention provides a wind and light storage optimal configuration method and system considering spot market and capacity electricity price. The method comprises the following steps: acquiring technical and economic parameters of each element in project planning, and acquiring market operation environment data of the project planning; based on the technical economic parameters and the market operation environment data, constructing and solving a total factor optimization model; in response to an optimization result which is obtained by solving and meets the optimization target, determining an investment return rate of project planning in combination with the market operation environment data; and in response to the fact that the investment return rate does not meet the preset threshold requirement, executing a solving cycle by taking the adjustment scale parameter as a start until the investment return rate meeting the preset threshold requirement is obtained, and taking an optimization result obtained by current cycle solving as a configuration result of project planning. According to the invention, economic optimal configuration of wind and light storage cluster energy storage under the conditions of adapting to spot market fluctuation and obtaining capacity electricity price income is realized, and the reliability and economical efficiency of project planning are effectively improved.

The application discloses a kind of based on layered reinforcement learning's building multi-energy network collaborative control method and device, comprising:1.building the physical model system of building multi-energy network;2.building the double-flow load forecasting model of residual reinforcement learning, based on asymmetric reward calculation output final load prediction value;3.design layered reinforcement learning-based decision framework, including different operating frequency's high-level management network and bottom execution network;4.build multi-dimensional heterogeneous state space and composite action space;5.design to introduce bottom soft protection mechanism and the evaluation system of nonlinear reward, solve multi-objective conflict and eliminate model boundary overrun risk;6.input real-time state to the optimal layered reinforcement learning model trained, output deterministic instruction execution closed-loop online scheduling.The application is applicable to the multi-energy collaborative scheduling scene of complex building, can give the robust regulation and control scheme of economic optimum under the premise of guaranteeing user comfort and system physical safety.