Search

Aiming at the problems that the penalty factor and kernel function parameters of SVM（support vector machine） are easy to fall into the local optimal solution in the optimization process and the Harris Hawks optimization algorithm is easy to fall into the local optimal solution， a method of using IHHO （improved Harris Hawks optimization） algorithm to optimize the penalty factor and kernel function parameters of SVM and constructing IHHO-SVM classifier to identify disturbance signals of power quality is proposed. By adding 0 dB，20 dB and 30 dB Gaussian white noises to nine different disturbance signals of power quality， the improved empirical mode decomposition algorithm of adaptive noise complete set is used to decompose the signal， and the energy entropy and sample entropy of the first three intrinsic mode function components of the signal are extracted as a set of feature vectors. The feature vectors are normalized and input into nine classifiers for comparison. The simulation results show that the recognition accuracy of IHHO-SVM classifier is 99.11%， 97.78% and 97.33%， respectively， when the signal is added with 0 dB，20 dB and 30 dB Gaussian white noises. The classification effect of IHHO-SVM classifier is the best among all classifiers， which proves the accuracy， superiority and noise immunity of its classification.

Accurate power load forecasting is crucial to the safe and stable operation of power systems. In the context of spot market, the dynamically changing real-time market tariff gives the “commodity” property of electricity and changes the electricity consumption behavior of customers and the electricity consumption at each time, which significantly aggravates the difficulty of electricity load forecasting. To address the problems of many influencing factors, difficult input sequence selection and insufficient feature extraction capability of the prediction model, we propose a hybrid prediction model that combines novel input sequence selection and longitudinal crossover algorithm (CSO) to optimize deep belief networks. Firstly, the real-time electricity price is incorporated as an influencing factor into the prediction model input, which improves the prediction model influencing factor system in the market environment; secondly, the similarity between the historical load sequence influencing factor and the sequence of load influencing factors of the day to be predicted is considered from two perspectives of distance and trend, and the historical load sequence is reasonably selected using the comprehensive similarity, and then the prediction model input sequence is determined; finally, the deep belief Finally, the load forecasting model is constructed by using deep belief network, and the key parameters such as threshold value of the forecasting model are optimized by CSO algorithm to achieve accurate power load forecasting. The proposed hybrid forecasting model is validated by comparing and analyzing the forecasting results of different input sequences and different methods with the simulation of Singapore electricity market data. In addition, input series of different time scales are set to find the best sample set to avoid the reduction of forecasting accuracy caused by data redundancy in the sample set, and a sample set of 6 months is appropriate for load forecasting by the method in this paper.

Abstract The renewable energy system integrates various power generating units, heating units, energy conversion devices, and energy storage devices, which is an effective way to improve energy efficiency and realize clean energy utilization. In this paper, a renewable energy system integrating with photovoltaic electric power generation systems, wind‐driven generators, gas‐driven generators, gas‐fired boilers, electric chillers, electric and heating energy storage devices is constructed in an isolated tourist area. Considering the complex multi‐energy flows in renewable energy systems, an energy hub with power and heat is established to concentrate and distribute electric and heating energy flow for balancing energy supply and demand in a CCHP system. Introducing the constraints of renewable energy penetration index and energy supply reliability index, a collaborative optimization framework for system configuration is constructed to minimize annual capital cost, fuel cost, and maintenance cost. The simulation results show that the model and algorithm in this paper are feasible and applicable, and the optimization scheme has good economic benefits and optimal performance, which can promote the consumption of renewable energy and reduce the surplus of electric energy and heat energy.

A multi-energy system can supply both electric and thermal energy simultaneously to the end-users to achieve a high energy use-efficiency. However conventional operational strategies for multi-energy systems, in the existing works, do not consider renewable energy generation plants and CCHP plants as belonging to different interests. To cope with this problem, this article studies a cooperative operation framework model for a Wind-Solar-CCHP Multi-energy system. Instead of the conventional non-cooperative solution-based method, the optimal operation scheduling problem of a multi-energy system is described as an optimization problem of Nash Bargaining. Then the optimization problem of Nash Bargaining for the multi-energy system decomposed into two subproblems: social welfare maximization problem (P1) and energy trading payment problem (P2). The optimal energy transaction profiles can be obtained by solving the P1 problem and the problem of payment of energy trading between PV, WT plant agents and the CCHP plant agent can be obtained by solving the P2 problem. Both problems P1 and P2 can be formulated into mixed-integer linear programming problems and solved by the alternating directional multiplier method. Numerical studies demonstrate the correctness and effectiveness of the proposed cooperative operation framework and distributed algorithm for solving the two subproblems. Moreover, the bargaining-based cooperative operation method can further induce the multi-energy system to improve the operating profit with the reduced feed-in tariff of distributed generation.

The multi-energy system is a promising energy-efficient technology to supply electric and thermal energy to end-users simultaneously, which can realize the energy cascade utilization. However, it is challenging to optimize the operation of multi-energy systems due to their inherent structural complexity, as well as the highly coupled nature of multiple energy flows and the uncertainty of renewable energy generation. This paper proposed a collaborative demand-controlled operation strategy for a multi-energy system, which consists of an upper-level model and a lower-level model. In the upper-level model, a robust linear optimization method is adopted to optimize the system operation in a day-ahead stage. In the lower-level model, a stochastic rolling optimization method is applied to achieve a dynamic adjustment to cope with the fluctuation in both renewable electricity generation and electric load. The multiple energy demand-controlled strategy is also applied in the optimal operation strategy to achieve load shifting and to create flexibility in energy demand despite the “source-load” imbalance power fluctuation. A case study is carried out and simulation results verify the effectiveness and correctness of the proposed model of the coordinated operation framework.

A stochastic fuzzy chance-constrained programming model with multi-objective optimization for coordinated control of power loss and voltage in distribution systems with renewable energy is presented by taking power output of DGs and charging-discharging power of EVs as random fuzzy variables and load power as random variables. Considering the fuzziness and randomness of active power output of distributed generation systems with wind and solar energy and charging power of electric vehicles, the key parameters of probability density function are determined by fitting incomplete data of uncertainties such as wind speed, sunlight intensity and charging power of electric vehicles. According to the principle of random fuzzy compatibility, the probability density function of the uncertainties is transformed into the probability distribution function of the uncertainties. The NDC(Normal Distribution Crossover)-based non-dominated sorting genetic algorithm is used to solve the optimization problem, and the Pareto solution set of the multi-objective optimization problem is obtained. The feasibility and applicability of the proposed model and algorithm are verified by simulating IEEE-33 and IEEE-118 distribution system.

The optimal operation of a combined cooling, heating and power (CCHP) system depends on its structure and adopted energy dispatch strategies. This paper proposes a matrix modeling method for the CCHP system structure, in which multi-energy supply is regarded as the input of system, and cooling, heating, electric load as the output of the system. The energy flow from the system input to output includes the scheduling matrix, the efficiency matrix, and the energy conversion matrix model. Adopt mixed rolling-horizon and particle swarm optimization algorithm to allocation the system scheduling factor to promote optimal operation of CCHP systems. According to the characteristics of input and output energy flow in different seasons of a certain area, the system is simulated and calculated. The results show that the adoption of rolling-horizon optimization for the thermal-electric load in winter can fully calculate the three scheduling strategies and select the optimal strategy in the rolling window. Compared to other methods, the optimization of scheduling factors in summer highlights the low-cost benefits.