9results about How to "Optimizing Scheduling Strategy" patented technology

The invention relates to a self-adaptive closed-loop context engineering method and device based on an intelligent agent, and belongs to the technical field of intelligent agents, and the method comprises the steps: outputting a context scheduling action intention for a current task stage through a reinforcement learning scheduling model in a decision-making layer based on a task type, a task demand and a current task state prediction decision; wherein the context scheduling action intention of the current task stage is an execution action in a predefined action space; mapping the action intention into at least one specific operation which can be triggered and executed on the execution layer on the execution layer, scheduling the action intention based on the context of the current task stage, and setting an execution condition for triggering the specific operation; and triggering and executing the corresponding specific operation based on the execution condition of the specific operation to obtain the task execution result, so that the intelligent agent can dynamically manage at least one of the context window, the associated memory network and the sub-intelligent agent cluster of the LLM intelligent agent, thereby being beneficial to improving the application efficiency of the intelligent agent.

The invention discloses a computing power demand prediction and resource pre-distribution system based on deep learning, and relates to the technical field of artificial intelligence and computing resource scheduling management, and the system comprises a data collection fusion module, a demand prediction and correction module, a strategy generation and verification module, and a model updating module. And the data acquisition and fusion module is used for acquiring multi-source heterogeneous data and carrying out preprocessing and feature fusion on the data. According to the computing power demand prediction and resource pre-distribution system based on deep learning, a prediction process containing multi-source data fusion and having a dual detection and correction mechanism is constructed, so that the dynamics and uncertainty of the computing power demand are effectively coped with; by means of the design, the prediction result can still keep high credibility in the data exception or burst mode, a stable and reliable data basis is provided for subsequent resource decision making, and therefore the risk of scheduling errors caused by prediction deviation is reduced from the source.

This invention provides a robust optimization scheduling method and system for virtual power plants considering multiple uncertainties, relating to the field of power market dispatching technology. The method includes: establishing a virtual power plant dispatching model based on ARIMA-SVR, where uncertainties include distributed energy generation, electricity prices, and load demand; extracting features of the uncertainties, constructing an uncertainty set, and transforming the virtual power plant dispatching model into a robust optimization scheduling model; and using a particle swarm optimization algorithm to solve the robust optimization scheduling model and optimize the dispatching strategies for each energy resource within the virtual power plant. This invention, by constructing a robust optimization scheduling model considering multiple uncertainties and combining it with advanced solving algorithms, achieves optimized dispatching of virtual power plants in complex market environments, improving the dispatching efficiency, economic benefits, and ability to cope with uncertainties in complex market environments.

This invention discloses a method and system for coordinated scheduling of two-way arbitrage and demand response by energy storage aggregators. Through an innovative business model, it enables energy storage aggregators to achieve two-way arbitrage in both wholesale and retail markets, as well as multiple value acquisitions through collaborative demand response with industrial and commercial parks. This invention constructs a mixed-integer linear programming optimization model with the objective of maximizing the aggregator's total day-ahead revenue, accurately characterizing the aggregator's trading behavior and energy storage operation constraints in a multi-market environment. Addressing the nonlinear effective response capacity segmentation calculation and evaluation mechanism in demand response rules, this invention proposes a piecewise linearization method based on auxiliary binary variables and the Big-M method, accurately transforming complex nonlinear constraints into standard linear constraints. This method can effectively coordinate the optimal allocation of energy storage among multiple revenue sources, including wholesale market price arbitrage, retail market revenue sharing, and demand response compensation, significantly improving the economic benefits of energy storage aggregators and providing a scientific decision support tool for the commercial operation of energy storage aggregators.

The invention discloses an agricultural integrated energy park optimization control method considering environmental capacity constraints, which optimizes a multi-energy scheduling strategy and improves energy utilization efficiency. The method comprises the following steps: firstly, constructing a multi-energy system operation control and pollution emission model, quantifying the influence of pollution emission on the environment, introducing environment capacity constraint, and evaluating and dynamically adjusting an energy scheduling strategy in real time; and then, proposing an optimization control model based on a fuzzy membership degree, and processing a nonlinear relationship between agricultural production requirements and energy supply by adopting a fuzzy theory. Secondly, providing a comprehensive planning method based on environmental capacity evaluation, and solving a long-term energy configuration scheme by adopting dynamic planning; and finally, proposing an optimization control model based on data driving, predicting an energy demand and a pollution emission trend by adopting a deep learning algorithm, dynamically adjusting an operation strategy, and ensuring efficient operation of the system under the constraint of the environmental capacity. According to the invention, energy-environment collaborative management can be realized, the operation efficiency is improved, and sustainable development is promoted.

The invention provides a multi-energy coupling system model prediction control method and system based on a Jacobi function, and the method comprises the steps: building energy coupling models of a multi-energy coupling system based on a Jacobi elliptic function, and the energy coupling models comprise an energy demand model, an energy supply model and a multi-energy coupling dynamic model; combining an ARMA model and a Jacobi elliptic function, and constructing a hybrid prediction model based on an energy demand model; and constructing a model prediction control framework by using the multi-energy coupling dynamic model and the hybrid prediction model, and obtaining a prediction control decision of the multi-energy coupling system by the model prediction control framework according to the current state of the multi-energy coupling system.

The application provides a kind of intelligent traffic light scheduling method and system combined with edge computing, it is related to traffic signal optimization scheduling field, method includes: monitoring and obtaining the traffic correlation data of target area in historical time zone;The red-green light scheduling optimization analysis of target area in preset time zone is carried out, and the first optimization scheduling strategy is generated, which includes a plurality of control schemes of a plurality of red-green lights in the target area;A plurality of control schemes are mapped and transmitted to a plurality of edge processing units of a plurality of red-green lights, and a plurality of red-green lights are dynamically scheduled.The purpose is to solve the problem that the traditional method is often based on fixed time period, cannot dynamically adjust according to real-time traffic flow, road conditions and weather factors, etc., leading to traffic congestion, waste of resources and other problems;By combining cloud and edge computing, the red-green light scheduling strategy is generated and optimized, which can dynamically adjust according to the real-time flow, road conditions and weather changes of each intersection, and optimize the operation efficiency of the whole traffic system.

The invention relates to a thermal power plant scheduling method and device, electronic equipment, a storage medium and a program product, relates to the technical field of intelligent scheduling, and can dynamically respond to supply and demand changes and optimize a power supply and heat supply scheduling strategy. The method comprises the following steps: acquiring multi-source data of a thermal power plant, wherein the real-time multi-source data comprises power supply data, heat supply data and external data; a heat supply distribution weight is determined according to the external data, a power supply demand is obtained through prediction according to the power supply data, a heat supply demand is obtained through prediction according to the heat supply data, and a supply and demand satisfaction index of the thermal power plant is determined at least according to the heat supply distribution weight, the power supply demand and the heat supply demand; the supply and demand satisfaction index is substituted into a target function, the minimum supply and demand satisfaction index is taken as a target, the target function is solved according to preset constraint conditions, and a target scheduling strategy is generated; and scheduling power supply and heat supply of the thermal power plant according to the target scheduling strategy.

This invention proposes a method and system for economic and environmental dispatching of multi-regional power systems based on bi-level programming. With the goal of minimizing the power generation cost of generator sets and minimizing the emission of pollutants, the regional economic and environmental dispatching problem is transformed into bi-level programming, thereby reducing the difficulty of solving the multi-regional economic emission dispatching problem and obtaining a more flexible dispatching strategy.