•An improved min-max dispatching method for grid-connected PV units was developed.•A control algorithm for short-term power dispatching was proposed.•The capacity and operation of battery energy ...storage system are optimized.•Efficient collaboration with the transmission system operator is realized.•High battery utilization is realized.
High uncertainty and large fluctuation of variable renewable energy create enormous challenges to planning and operation of integrated energy systems. To overcome these problems, this paper proposed an improved min-max dispatching method. In the meantime, a control algorithm for short-term power dispatching was proposed and implemented to smoothen the power dispatching between two neighboring dispatching intervals. The improved min-max dispatching method was applied to a 1 kW experimental PV system with real-time data. The optimal capacity of the battery energy storage system obtained by the improved min-max method is 40% smaller than the volume obtained by the modified min-max method. Regarding the operation of the BESS, the average depth of discharge is 0.5988, which is 7.06% higher than the operation performance with the alternative dispatching method. The results clearly indicate that improved min-max dispatching method is a very effective approach for managing grid-connected integrated energy systems and promoting penetration of variable renewable energies.
The rapid development of renewable energy and the continuous growth of peak load bring new challenges to the dispatching capacity of generation side. In view of the possible mismatch between power ...generation of renewable energy and the load, we propose an integrated optimal dispatching strategy model of power generation and consumption interaction in this paper. Among them, the generation side resources include wind power, photovoltaic and battery energy storage and the load side dispatching resources include transferable load, interruptible load and electric vehicles. The model takes the benefits of generation side and the benefits of load side as objectives. Moreover, three different dispatching orders are put forward, which are random dispatching, interruption and transfer of load before electric vehicles charging and discharging, electric vehicles charging and discharging before interruption and transfer of load. In addition, we propose seven different dispatching combinations based on the optimal dispatching order to analyse the response ability of different load side dispatching resources. Multi-objective Genetic Algorithm and the method of technique for order preference by similarity to an ideal solution are applied in this study to obtain the optimal results. It can be identified that the response ability of different load side dispatching resources is different, and the overall dispatching can improve the benefits of generation side and the benefits of load side. Meanwhile, the proposed strategy considers the willingness of the load to the greatest extent and effectively improves the utilization rate of wind and solar power generation.
A scheduling policy strongly influences the performance of a manufacturing system. However, the design of an effective scheduling policy is complicated and time consuming due to the complexity of ...each scheduling decision, as well as the interactions among these decisions. This paper develops four new multi-objective genetic programming-based hyperheuristic (MO-GPHH) methods for automatic design of scheduling policies, including dispatching rules and due-date assignment rules in job shop environments. In addition to using three existing search strategies, nondominated sorting genetic algorithm II, strength Pareto evolutionary algorithm 2, and harmonic distance-based multi-objective evolutionary algorithm, to develop new MO-GPHH methods, a new approach called diversified multi-objective cooperative evolution (DMOCC) is also proposed. The novelty of these MO-GPHH methods is that they are able to handle multiple scheduling decisions simultaneously. The experimental results show that the evolved Pareto fronts represent effective scheduling policies that can dominate scheduling policies from combinations of existing dispatching rules with dynamic/regression-based due-date assignment rules. The evolved scheduling policies also show dominating performance on unseen simulation scenarios with different shop settings. In addition, the uniformity of the scheduling policies obtained from the proposed method of DMOCC is better than those evolved by other evolutionary approaches.
The integrated ride-sourcing mode, developed by third-party integrators, is a feasible solution to market fragmentation because it integrates travel demand and vehicle supply. However, intense ...competition between platforms reduces the efficiency of the dispatching process. To tackle this issue, a two-stage dispatching framework is proposed, utilizing a partially observable Markov decision process (POMDP) to model the dispatching problem as a mixed cooperative-competitive reinforcement learning task. Within this framework, the Multi-Graph Hierarchical Multi-Head Attention-Deep Deterministic Policy Gradient (MGHMHA-DDPG) algorithm is proposed to determine the generalized values of driver-passenger pairs. A combinatorial optimization model is then formulated to identify the dispatching scheme that maximizes these values. Furthermore, the MGHMHA-DDPG algorithm incorporates a multi-graph convolutional module, a hierarchical multi-head attention module, and a gated recurrent module to model the global supply-demand distribution, the cooperation potential of vehicles, and the hidden features of the temporal dimension, respectively. Experiments using Beijing-based data demonstrate that the MGHMHA-DDPG algorithm outperforms benchmark methods in terms of market revenues and order response rates. This indicates that the MGHMHA-DDPG algorithm effectively mitigates dispatching conflicts between platforms and enhances overall market efficiency.
Manufacturing is involved with complex job shop scheduling problems (JSP). In smart factories, edge computing supports computing resources at the edge of production in a distributed way to reduce ...response time of making production decisions. However, most works on JSP did not consider edge computing. Therefore, this paper proposes a smart manufacturing factory framework based on edge computing, and further investigates the JSP under such a framework. With recent success of some AI applications, the deep Q network (DQN), which combines deep learning and reinforcement learning, has showed its great computing power to solve complex problems. Therefore, we adjust the DQN with an edge computing framework to solve the JSP. Different from the classical DQN with only one decision, this paper extends the DQN to address the decisions of multiple edge devices. Simulation results show that the proposed method performs better than the other methods using only one dispatching rule.
With the emerging concept of sharing-economy, shared electric vehicles (EVs) are playing a more and more important role in future mobility-on-demand traffic system. This article considers joint ...charging scheduling, order dispatching, and vehicle rebalancing for large-scale shared EV fleet operator. To maximize the welfare of fleet operator, we model the joint decision making as a partially observable Markov decision process (POMDP) and apply deep reinforcement learning (DRL) combined with binary linear programming (BLP) to develop a near-optimal solution. The neural network is used to evaluate the state value of EVs at different times, locations, and states of charge. Based on the state value, dynamic electricity prices and order information, the online scheduling is modeled as a BLP problem where the decision variables representing whether an EV will 1) take an order, 2) rebalance to a position, or 3) charge. We also propose a constrained rebalancing method to improve the exploration efficiency of training. Moreover, we provide a tabular method with proved convergence as a fallback option to demonstrate the near-optimal characteristics of the proposed approach. Simulation experiments with real-world data from Haikou City verify the effectiveness of the proposed method.
Efficient truck dispatching is crucial for optimizing container terminal operations within dynamic and complex scenarios. Despite good progress being made recently with more advanced ...uncertainty-handling techniques, existing approaches still have generalization issues and require considerable expertise and manual interventions in algorithm design. In this work, we present deep reinforcement learning-assisted genetic programming hyper-heuristics (DRL-GPHH) and their ensemble variant (DRL-GPEHH). These frameworks utilize a reinforcement learning agent to orchestrate a set of auto-generated genetic programming (GP) low-level heuristics, leveraging the collective intelligence, ensuring advanced robustness and an increased level of automation of the algorithm development. DRL-GPEHH, notably, excels through its concurrent integration of a GP heuristic ensemble, achieving enhanced adaptability and performance in complex, dynamic optimization tasks. This method effectively navigates traditional convergence issues of deep reinforcement learning (DRL) in sparse reward and vast action spaces, while avoiding the reliance on expert-designed heuristics. It also addresses the inadequate performance of the single GP individual in varying and complex environments and preserves the inherent interpretability of the GP approach. Evaluations across various real port operational instances highlight the adaptability and efficacy of our frameworks. Essentially, innovations in DRL-GPHH and DRL-GPEHH reveal the synergistic potential of reinforcement learning and GP in dynamic truck dispatching, yielding transformative impacts on algorithm design and significantly advancing solutions to complex real-world optimization problems.
Vehicle dispatching in the mobility-as-a-service (MaaS) market has gradually become a situation of multi-service provider competition and coexistence. However, most existing research on vehicle ...dispatching with dynamic pricing for the MaaS market is still limited to single-service provider scenarios. In this paper, we propose an economic model that analyzes the vehicle dispatching service pricing and demand interactions between multiple mobility service providers (MSPs) and passengers, respectively. We formulate the vehicle dispatching service pricing and demand problem as a two-stage Stackelberg game under different pricing schemes, namely, independent pricing scheme (IPS) and competitive pricing scheme (CPS), considering the vehicle supply-demand relationship and market competition among the MSPs. The MSPs, as leaders, set their service pricing strategies first, and then the passengers, as the followers, determine their service demands. Due to the high-dimensional and complicated nature of the dynamic MaaS market environment, we develop a multi-agent deep reinforcement learning (MADRL) algorithm to achieve the Nash equilibrium (NE) of the formulated game, which indicates the optimal pricing and demand strategies for MSPs and passengers. Simulation results and analysis show that the proposed MADRL-based algorithm converges to the optimal solution and outperforms other benchmark schemes under both IPS and CPS in terms of maximizing MSPs' revenue and protecting passengers' benefits. Furthermore, the proposed MADRL-based algorithm under CPS improves MSPs' market attractiveness and long-term benefits, which encourages MSPs to participate in competitive vehicle dispatching in the MaaS market.
Plug-in electric vehicles (PEVs) are increasingly popular in the global trend of energy saving and environmental protection. However, the uncoordinated charging of numerous PEVs can produce ...significant negative impacts on the secure and economic operation of the power system concerned. In this context, a hierarchical decomposition approach is presented to coordinate the charging/discharging behaviors of PEVs. The major objective of the upper-level model is to minimize the total cost of system operation by jointly dispatching generators and electric vehicle aggregators (EVAs). On the other hand, the lower-level model aims at strictly following the dispatching instructions from the upper-level decision-maker by designing appropriate charging/discharging strategies for each individual PEV in a specified dispatching period. Two highly efficient commercial solvers, namely AMPL/IPOPT and AMPL/CPLEX, respectively, are used to solve the developed hierarchical decomposition model. Finally, a modified IEEE 118-bus testing system including 6 EVAs is employed to demonstrate the performance of the developed model and method.
With proliferation of smart phones and an increasing number of services provisioned by clouds, it is commonplace for users to request cloud services from their mobile devices. Accessing services ...directly from the Internet data centers inherently incurs high latency due to long RTTs and possible congestions in WAN. To lower the latency, some researchers propose to `cache' the services at edge clouds or smart routers in the access network which are closer to end users than the Internet cloud. Although `caching' is a promising technique, placing the services and dispatching users' requests in a way that can minimize the users' access delay and service providers' cost has not been addressed so far. In this paper, we study the joint optimization of service placement and load dispatching in the mobile cloud systems. We show this problem is unique to both the traditional caching problem in mobile networks and the content distribution problem in content distribution networks. We develop a set of efficient algorithms for service providers to achieve various trade-offs among the average latency of mobile users' requests, and the cost of service providers. Our solution utilizes user's mobility pattern and services access pattern to predict the distribution of user's future requests, and then adapt the service placement and load dispatching online based on the prediction. We conduct extensive trace driven simulations. Results show our solution not only achieves much lower latency than directly accessing service from remote clouds, but also outperforms other classical benchmark algorithms in term of the latency, cost and algorithm running time.